Modeling stochastic dynamics from discrete observations is a key interdisciplinary challenge. Existing methods often fail to estimate the continuous evolution of probability densities from trajectories or face the curse of dimensionality. To address these limitations, we presents a novel paradigm: modeling dynamics directly in the weight space of a neural network by projecting the evolving probability distribution. We first theoretically establish the connection between dynamic optimal transport in measure space and an equivalent energy functional in weight space. Subsequently, we design WeightFlow, which constructs the neural network weights into a graph and learns its evolution via a graph controlled differential equation. Experiments on interdisciplinary datasets show that WeightFlow improves performance by an average of 43.02\% over state-of-the-art methods, providing an effective and scalable solution for modeling high-dimensional stochastic dynamics.

Large language models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, yet the multi-step reasoning processes often lead to expensive computation cost.The recent advance of diffusion language models (DLMs) adopts a parallel, non-autoregressive generation mechanism, which enables the efficient production of multiple outputs.In this paper, we explore a collaborative reasoning framework that combines diffusion-based generation with autoregressive evaluation.Specifically, we leverage DLMs to efficiently propose stepwise reasoning thoughts, and employ LLMs as evaluators to assess and select candidates based on their plausibility and correctness.By decoupling proposal generation from evaluation, our framework exploits the strengths of both models: efficient exploration from diffusion models and causally grounded assessment from autoregressive models, which naturally aligns with the divergent-convergent thinking framework in cognitive psychology.Experiments across various mathematical and logical reasoning benchmarks demonstrate that, our framework improves inference efficiency while maintaining competitive or superior reasoning accuracy, laying the groundwork for building efficient reasoning architectures.Our code is open-source at https://anonymous.4open. science/r/

Haotian Xu, Yue Hu, Zhengqiu Zhu, Chen Gao, Ziyou Wang, Junreng Rao, Wenhao Lu, Weishi Li, Quanjun Yin, Yong Li. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

ACM’s transition to full open access (OA) may fundamentally reshape publication practices within the SIGCHI community. However, the current state of OA adoption and the potential impact of this shift remain underexplored, which limits both scholarly understanding and informed actions. To address this gap, we conduct a large-scale bibliometric analysis of SIGCHI publications from 2001 to 2024. We document the prevalence of OA in our community and author characteristics associated with OA uptake, and assess the projected impact of the transition regarding financial cost and scholarly visibility. Our results indicate that our community is well-positioned for this shift, with fewer than 10.1% of the papers expected to incur additional OA fees. This move to OA is likely to boost citations, especially cross-community citations, but risks further marginalizing under-resourced authors. We discuss the broader implications of these findings for fostering a sustainable future for our community.

Fine-grained wildfire spread prediction is crucial for enhancing emergency response efficacy and decision-making precision. However, existing research predominantly focuses on coarse spatiotemporal scales and relies on low-resolution satellite data, capturing only macroscopic fire states while fundamentally constraining high-precision localized fire dynamics modeling capabilities. To bridge this gap, we present FireSentry, a provincial-scale multi-modal wildfire dataset characterized by sub-meter spatial and sub-second temporal resolution. Collected using synchronized UAV platforms, FireSentry provides visible and infrared video streams, in-situ environmental measurements, and manually validated fire masks. Building on FireSentry, we establish a comprehensive benchmark encompassing physics-based, data-driven, and generative models, revealing the limitations of existing mask-only approaches. Our analysis proposes FiReDiff, a novel dual-modality paradigm that first predicts future video sequences in the infrared modality, and then precisely segments fire masks in the mask modality based on the generated dynamics. FiReDiff achieves state-of-the-art performance, with video quality gains of 39.2% in PSNR, 36.1% in SSIM, 50.0% in LPIPS, 29.4% in FVD, and mask accuracy gains of 3.3% in AUPRC, 59.1% in F1 score, 42.9% in IoU, and 62.5% in MSE when applied to generative models. The FireSentry benchmark dataset and FiReDiff paradigm collectively advance fine-grained wildfire forecasting and dynamic disaster simulation. The processed benchmark dataset is publicly available at: https://github.com/Munan222/FireSentry-Benchmark-Dataset.

The rapid advancement of large language models (LLMs) has opened new possibilities for understanding users in search and recommendation. While traditional behavior-based or feature-driven user models rely primarily on explicit interactions or handcrafted representations, LLMs introduce a fundamentally different paradigm: LLM-powered user profiling, where user preferences, intents, and contextual attributes can be extracted, summarized, or reasoned about directly through natural language. This shift unlocks powerful new paths to achieve personalization but also raises pressing questions related to modeling fidelity, temporal dynamics, evaluation methodology, privacy, and responsible deployment. The LLM-UP workshop aims to bring together researchers and practitioners to systematize emerging progress in LLM-powered user profiling, identify open challenges, and explore opportunities for integrating such techniques into search and recommendation pipelines. The LLM-UP workshop adopts an interactive structure featuring lightning talks, panel discussions, and paper presentations to foster active engagement, cross-disciplinary dialogue, and community-driven agenda setting for this rapidly evolving field.

Forecasting state evolution of network systems, such as the spread of information on social networks, is significant for effective policy interventions and resource management. However, the underlying propagation dynamics constantly shift with new topics or events, which are modeled as changing coefficients of the underlying dynamics. Deep learning models struggle to adapt to these out-of-distribution shifts without extensive new data and retraining. To address this, we present Zero-Shot Forecasting of Network Dynamics through Weight Flow Matching (FNFM), a generative, coefficient-conditioned framework that generates dynamic model weights for an unseen target coefficient, enabling zero-shot forecasting. Our framework utilizes a Variational Encoder to summarize the forecaster weights trained in observed environments into compact latent tokens. A Conditional Flow Matching (CFM) module then learns a continuous transport from a simple Gaussian distribution to the empirical distribution of these weights, conditioned on the dynamical coefficients. This process is instantaneous at test time and requires no gradient-based optimization. Across varied dynamical coefficients, empirical results indicate that FNFM yields more reliable zero-shot accuracy than baseline methods, particularly under pronounced coefficient shift.

The forecasting of mobile data not only helps operators proactively perceive the network status, enabling them to arrange and schedule network resources in advance to improve user service quality, but also allows for the on-demand, flexible extrapolation of network changes under different strategies, effectively reducing the trial-and-error costs in the live network. Traditional prediction methods with tailored models for exclusive data types undoubtedly increase the design complexity and deployment costs. In this paper, we propose a Mobile Foundation Model (MobiFM) for data forecasting, which adopts a unified framework to forecast mobile data with diverse types (mobile traffic, users, and wireless channel), various time granularities (hourly and minute-level), and multiple spatial scales (cell-level and grid-level). MobiFM is a generative model built on diffusion and Transformer backbones. It incorporates a memory-network core that flexibly stores large amounts of contextual knowledge from urban environments, network configuration parameters, and spatio-temporal features. In parallel, MobiFM employs Mixture-of-Experts (MoE) networks to specialize and exploit the distinct characteristics of heterogeneous mobile data. We train the MobiFM using 10 real-world datasets with over 200,000 time-series points, totaling more than 1 billion tokens. The experimental results demonstrate that MobiFM achieves improvements of 20.24%, 10.92%, and 6.52% in the forecasting of mobile traffic, users, and wireless channel data, respectively, exhibiting good generalization performance compared to the baselines. Furthermore, based on MobiFM’s forecasting capability, we formulate an energy-saving optimization case, where the experimental results show the MobiFM-based scheme can improve energy efficiency up to 17.9%.

Aspect-based sentiment analysis (ABSA) aims to identify aspects and their associated sentiments from text. It can be categorized into explicit sentiment analysis (ESA) and implicit sentiment analysis (ISA). Unlike ESA, ISA lacks explicit sentiment indicators, requiring deeper contextual understanding and multilevel reasoning to infer underlying opinions. To address this challenge, we propose a progressive chain-of-thought-based reasoning framework (P-CoR) inspired by advanced prompt engineering in large language models (LLMs). P-CoR consists of three progressive prompting strategies: chain-of-thought-based reasoning (CoR), chain self-consistency-based reasoning (CSCR), and tree-of-thought-based reasoning (ToR). In CoR, we adopt a three-step reasoning process to identify fine-grained aspects, infer aspect-level opinions, and predict sentiment polarity. ToR involves identifying all aspect terms and subsequently determining the intensity of sentiment and the underlying reasons for opinions associated with each aspect, while CSCR enhances robustness by selecting candidate answers through voting consistency across inferred aspects and opinions. Experimental results on two benchmark datasets show that all proposed strategies outperform traditional neural models, with ToR achieving the best overall performance. Specifically, ToR attains 86.12% accuracy and 79.22% Macro-F1 on the restaurant dataset and 83.09% accuracy with 83.90% Macro-F1 on the laptop dataset. These results highlight the importance of ISA and validate the effectiveness of progressive prompting strategies for sentiment inference using LLMs.

Human trajectory data are crucial in urban planning, traffic engineering, and public health. However, directly using real-world trajectory data often faces challenges such as privacy concerns, data acquisition costs, and data quality. A practical solution to these challenges is trajectory generation, a method developed to simulate human mobility behaviors. Existing trajectory generation methods mainly focus on capturing individual movement patterns but often overlook the influence of population distribution on trajectory generation. In reality, dynamic population distribution reflects changes in population density across different regions, significantly impacting individual mobility behavior. Thus, we propose a novel trajectory generation framework based on a diffusion model, which integrates the dynamic population distribution constraints to guide high-fidelity generation outcomes. Specifically, we construct a spatial graph to enhance the spatial correlation of trajectories. Then, we design a dynamic population distribution aware denoising network to capture the spatiotemporal dependencies of human mobility behavior as well as the impact of population distribution in the denoising process. Extensive experiments show that the trajectories generated by our model can resemble real-world trajectories in terms of some critical statistical metrics, outperforming state-of-the-art algorithms by over 54%.

The coordinated deployment of multiple Base Stations (BS) and tuning of antenna configuration plays a crucial role in ensuring high-quality communication services, especially in the context of dense 5G BS deployment in megacities. However, traditional optimization methods, such as heuristics and Reinforcement Learning (RL), face challenges in addressing such problems involving the coordination of hundreds of BSs due to their limitations in handling the complexity and scale of large-scale scenarios. To address these challenges, this article proposes the Hierarchical Multi-Agent Proximal Policy Optimization with Representation Learning (HMAPPO-RL). By employing a hierarchical structure, we effectively decouple the optimization problem into two sub-problems: BS deployment and antenna parameter tuning. Different from the step-by-step method of optimizing the BS location and antenna, HMAPPO-RL achieves joint optimization of the two problems through an ingenious interactive mechanism, fully considering the mutual influence of the BS location and antenna. To address the large-scale challenge posed by hundreds of BSs, we utilize the upsampling and downsampling mechanisms of the UNet network to integrate global and local information from large-scale state information for performance enhancement. Since complex environmental information will cause great difficulties for the agent to evaluate the state value in large-scale scenarios, we add a representation learning module to enhance the accuracy of the agent’s state value estimation. The experiments using a precise mobile network simulator demonstrate the superiority of the proposed HMAPPO-RL, offering a comparative analysis with existing state-of-the-art methods. HMAPPO-RL achieves a coverage rate of 91.66% and an average throughput of 4,983,537 bit/s. These results represent improvements of 3.62% and 6.75% in coverage rate and throughput, respectively, when compared with the MAPPO algorithm.

The evolutionary dynamics of complex systems encode critical information about their functional organization. In particular, the generation times of edges reveal key aspects of historical development in networked systems such as protein-protein interaction networks, ecosystems, and social networks. Accurately recovering these temporal processes is of significant scientific value-for example, in elucidating the mechanisms underlying protein interaction evolution. However, existing methods typically assume access to partially time-stamped networks and often struggle to generalize across domains. They perform poorly in recovering edge generation times in static networks without temporal annotations. To address this challenge, we propose a comparative paradigm that enables cross-network learning by jointly training on multiple temporal networks. This framework captures structural-temporal correlations that generalize across networks and improves accuracy by 16.98% on average compared to separate training strategies. Furthermore, to mitigate the scarcity of real temporal data, we introduce a novel diffusion-based generative model for producing Augmented Temporal Networks (ATNs) . By integrating both real and generated samples during training, our joint strategy yields an additional 5.46% improvement in predictive accuracy, demonstrating the effectiveness of data augmentation in enhancing generalization.

Fine-grained air pollution forecasting is crucial for urban management and the development of healthy buildings. Deploying portable sensors on mobile platforms such as cars and buses offers a low-cost, easy-to-maintain, and wide-coverage data collection solution. However, due to the random and uncontrollable movement patterns of these non-dedicated mobile platforms, the resulting sensor data are often incomplete and temporally inconsistent. By exploring potential training patterns in the reverse process of diffusion models, we proposeSpatio-TemporalPhysics-InformedDiffusion Models (STeP-Diff). STeP-Diff leverages DeepONet to model the spatial sequence of measurements along with a PDE-informed diffusion model to forecast the spatio-temporal field from incomplete and time-varying data. Through a PDE-constrained regularization framework, the denoising process asymptotically converges to the convection-diffusion dynamics, ensuring that predictions are both grounded in real-world measurements and aligned with the fundamental physics governing pollution dispersion. To assess the performance of the system, we deployed 59 self-designed portable sensing devices in two cities, operating for 14 days to collect air pollution data. Compared to the second-best performing algorithm, our model achieved improvements of up to 89.12% in MAE, 82.30% in RMSE, and 25.00% in MAPE, with extensive evaluations demonstrating that STeP-Diff effectively captures the spatio-temporal dependencies in air pollution fields.

Mobile app usage behavior reveals human patterns and is crucial for stakeholders, but data collection is costly and raises privacy issues. Data synthesis can address this by generating artificial datasets that mirror real-world data. In this paper, we propose AppGen, an autoregressive generative model designed to generate app usage behavior based on users' mobility trajectories, improving dataset accessibility and quality. Specifically, AppGen employs a probabilistic diffusion model to simulate the stochastic nature of app usage behavior. By utilizing an autoregressive structure, AppGen effectively captures the intricate sequential relationships between different app usage events. Additionally, AppGen leverages latent encoding to extract semantic features from spatio-temporal points, guiding behavior generation. These key designs ensure the generated behaviors are contextually relevant and faithfully represent users' environments and past interactions. Experiments with two real-world datasets show that AppGen outperforms state-of-the-art baselines by over 12% in critical metrics and accurately reflects real-world spatio-temporal patterns. We also test the generated datasets in applications, demonstrating their suitability for downstream tasks by maintaining algorithm accuracy and order.

Simulation-based optimization has emerged as a crucial methodology in the field of mobile network optimization, addressing the need for dynamic and predictive network management. To address the scarcity of open-source mobile network simulators for advanced research, we developed GenNet—a generative AI-driven mobile network simulator. GenNet can create virtual replicas of mobile users, base stations, and wireless environments, utilizing generative AI methods to simulate the behaviors of these entities under various network settings with high accuracy. GenNet features a tailor-made API explicitly designed for reinforcement learning environments, enabling researchers to finely adjust network parameters such as tilts, azimuth, and transmitting power. Extensive experiments have utilized GenNet to benchmark multi-objective optimization algorithms, with a focus on enhancing network coverage, throughput, and energy efficiency, thereby validating its effectiveness as a robust platform for advancing network optimization techniques. Through this innovative tool, we aim to empower researchers and practitioners to identify and implement the most effective approaches for network optimization, paving the way for future advancements in mobile network management.

Urban spatio-temporal flow prediction, encompassing traffic flows and crowd flows, is crucial for optimizing city infrastructure and managing traffic and emergency responses. Traditional approaches have relied on separate models tailored to either grid-based data, representing cities as uniform cells, or graph-based data, modeling cities as networks of nodes and edges. In this paper, we build UniFlow, a foundational model for general urban flow prediction that unifies both grid-based and graph based data. We first design a multi-view spatio-temporal patching mechanism to standardize different data into a consistent sequential format and then introduce a spatio-temporal transformer architecture to capture complex correlations and dynamics. To leverage shared spatio-temporal patterns across different data types and facilitate effective cross-learning, we propose Spatio Temporal Memory Retrieval Augmentation (ST-MRA). By creating structured memory modules to store shared spatio-temporal patterns, ST-MRA enhances predictions through adaptive memory retrieval. Extensive experiments demonstrate that UniFlow outperforms existing models in both grid-based and graph-based f low prediction, excelling particularly in scenarios with limited data availability, showcasing its superior performance and broad applicability. The datasets and code implementation have been released on https://github.com/YuanYuan98/UniFlow.

Graph neural network-based recommenders employ the aggregation paradigms to learn node representation from higher-order neighboring nodes within the graph. However, these simple aggregation paradigms may perform poorly when mitigating noise impacts and capturing complex user preferences. To address it, some studies have attempted to enhance representation through contrastive augmentation across different views. Despite some effectiveness, the simple-view contrasts are still suboptimal with some unresolved challenges: (1) the influence of multivariate noise in interaction data, (2) knowledge biases introduced by irrelevant connections, and (3) user’s multiple interests. In this work, we propose a novel method named Diffusion-Based Relation Augmentation for Knowledge-aware Recommendation (DRAR) to overcome the above challenges. First, we alleviate the impact of interaction noise by injecting uncertainty and generating preference distributions with a diffusion-based module. Next, we design a relation augmentation module to effectively capture user neighborhood-level and context-level enhanced representations to alleviate the knowledge bias of irrelevant connections. Furthermore, we design a collaborative alignment module that enhances the model’s robustness by aligning user representation views at different stages. Extensive experiments on three benchmark datasets consistently demonstrate the superiority of our model over the state-of-the-art approaches. Our model demonstrates average improvements of 6.78% in Recall and 7.38% in NDCG across all datasets.

Click-Through Rate (CTR) prediction, which estimates the probability of a user clicking on a given item, is a critical task for online information services. Existing approaches often make strong assumptions that training and test data come from the same distribution. However, the data distribution varies since user interests are constantly evolving, resulting in the Out-of-Distribution (OOD) issue. In addition, users tend to have multiple interests, some of which evolve faster than others. Toward this end, we propose Disentangled Click-Through Rate Prediction (DiseCTR), which introduces a causal perspective of recommendation and disentangles multiple aspects of user interests to alleviate the OOD issue in recommendation. We conduct a causal factorization of CTR prediction involving user interest, exposure model, and click model, based on which we develop a deep learning implementation for these three causal mechanisms. Specifically, we first design an interest encoder with sparse attention which maps raw features to user interests and then introduce a weakly supervised interest disentangler to learn independent interest embeddings, which are further integrated by an attentive interest aggregator for prediction. Experimental results on three real-world datasets show that DiseCTR achieves the best accuracy and robustness in OOD recommendation against state-of-the-art approaches, significantly improving AUC and GAUC by over 0.02 and reducing logloss by over 13.7%. Further analyses demonstrate that DiseCTR successfully disentangles user interests, which is the key to OOD generalization for CTR prediction. We have released the code and data at https://github.com/DavyMorgan/DiseCTR/ .

With the widespread deployment of 5G networks, efficient network optimization and planning have become increasingly important. The generation of mobile traffic and user data can help network operators understand and grasp the network’s operational status from different perspectives, enabling customized strategies such as wireless resource allocation and user access control. However, existing research primarily focuses on the generation of single-type data and lacks exploration of the interplay between mobile traffic and user data. Moreover, current generative models struggle to capture the spatio-temporal correlations between multimodal environmental data and mobile data. In this paper, we propose a Multimodal Context-aware Diffusion Model (MCDiff) for simultaneously generating mobile traffic and users. The model incorporates an interplay perception module to capture the correlation between mobile traffic and users. To better characterize the complex and dynamic features of urban environments, we innovatively propose extracting both spatial and temporal variations from multimodal contextual data and employing contrastive learning to align multimodal contextual features with mobile data. Extensive experiments on two real-world datasets demonstrate that MCDiff can accurately generate both mobile traffic and users, achieving up to a 23.11% improvement in fidelity metrics. Facilitated by our multimodal contextual fusion module, MCDiff exhibits strong controllable and generalization capabilities, with a minimal transfer gap of only 1.19%. Furthermore, by leveraging the generated mobile traffic and user data, we formulate network planning and optimization strategies. Experimental results highlight the superiority and practicality of our method.

Mobile app usage data reveal user behavioral characteristics and is crucial for mobile operators for network service optimization, but its data collection is pricey and presents privacy concerns. Data synthesis, fortunately, can tackle this barrier by generating diverse and representative artificial datasets that resemble real-world data. In this paper, we propose SMAUG, a diffusion model-based generative model with large language models (LLMs) designed to generate personalized app usage data based on mobile users' mobility trajectories. To address the data inaccuracy issue brought by the sparsity nature of mobile app usage behavior, SMAUG decomposes the generation process and adopts a hierarchical structure framework to gradually refine the generation from the session level to the specific app level. By encoding spatio-temporal context and applying an attention mechanism, SMAUG effectively represents personalized user representations. Moreover, aiming to extensively explore the semantic information in app usage sessions, SMAUG incorporates LLMs to gain deeper insight into user behavior characteristics revealed in sessions, and also exploits a curriculum representation learning approach based on contrastive learning, exploring session characteristics from elementary to profound. Experiments on two real-world datasets show that SMAUG outperforms existing generative baseline approaches by over 25% under the metrics of RMSE, MAE, CRPS, JSD, M-TV, and Spearmanr. The model has also been successfully deployed to assist network service simulation, demonstrating their suitability for downstream tasks in real-world systems.

The rapid advancement of 5G networks has significantly increased the demand for high throughput and low latency, particularly for enhanced Mobile Broadband (eMBB) services. Optimizing user rates in large-scale base station (BS) collaborative scenarios is crucial, ensuring high throughput and low energy consumption while meeting the needs of users. The optimization process faces two key challenges: how to efficiently explore and utilize the vast action space for collaborative decision-making in large-scale networks with numerous BSs, and how to ensure optimal decision-making across numerous parameters while satisfying constraints. To tackle these challenges, we propose a novel solution that integrates a generative AI-powered Digital Twin platform with a multi-agent reinforcement learning (MARL) decision algorithm. An important tool is the high-fidelity DT-SimNet platform, enabling seamless integration with AI optimizers. Moreover, we propose a novel algorithm called Safe Hierarchical Multi-Agent Proximal Policy Optimization with Adaptive Prediction mechanism (Safe HMAPPO-AP). This algorithm integrates Safe MARL to ensure decision-making remains within constraint boundaries and incorporates a hierarchical structure to decompose the action space. Moreover, it leverages Graph Neural Networks (GNNs) for efficient feature extraction and employs the Adaptive Prediction mechanism to accelerate learning and improve network performance. Comprehensive experiments using the DT-SimNet platform demonstrate the superior performance of the proposed algorithm compared to competing methods. Within the target area, Safe HMAPPO-AP achieved a 6.73% improvement in average throughput for regular users and an 11.48% increase in system utility, while meeting demands of newly added eMBB users.

The increasing parameters and expansive dataset of large lan- guage models (LLMs) highlight the urgent demand for a technical solution to audit the underlying privacy risks and copyright issues associated with LLMs. Existing studies have partially addressed this need through an exploration of the pre-training data detection problem, which is an instance of a membership inference attack (MIA). This problem involves determining whether a given piece of text has been used during the pre-training phase of the target LLM. Although existing methods have designed various sophisticated MIA score functions to achieve considerable detection performance in pre-trained LLMs, how to achieve high-confidence detection and how to perform MIA on aligned LLMs remain challenging. In this paper, we propose MIA-Tuner, a novel instruction-based MIA method, which instructs LLMs themselves to serve as a more precise pre-training data detector internally, rather than design an external MIA score function. Furthermore, we design two instruction-based safeguards to respectively mitigate the privacy risks brought by the existing methods and MIA-Tuner. To comprehensively evaluate the most recent state-of-the-art LLMs, we collect a more up-to-date MIA benchmark dataset, named WIKIMIA-24, to replace the widely adopted benchmark WIKIMIA. We conduct extensive experiments across various aligned and unaligned LLMs over the two benchmark datasets. The results demonstrate that MIA-Tuner increases the AUC of MIAs from 0.7 to a significantly high level of 0.9.

Fanhang Man, Huandong Wang, Jianjie Fang, Zhaoyi Deng, Baining Zhao, Xinlei Chen, Yong Li. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

The Theory of Multiple Intelligences underscores the hierarchical nature of cognitive capabilities. To advance Spatial Artificial Intelligence, we pioneer a psychometric framework defining five Basic Spatial Abilities (BSAs) in Visual Language Models (VLMs): Spatial Perception, Spatial Relation, Spatial Orientation, Mental Rotation, and Spatial Visualization. Benchmarking 13 mainstream VLMs through nine validated psychometric experiments reveals significant gaps versus humans, with three key findings: 1) VLMs mirror human hierarchies (strongest in 2D orientation, weakest in 3D rotation) with independent BSAs; 2) Many smaller models surpass larger counterparts, with Qwen leading and InternVL2 lagging; 3) Interventions like CoT and few-shot training show limits from architectural constraints, while ToT demonstrates the most effective enhancement. Identified barriers include weak geometry encoding and missing dynamic simulation. By linking Psychometrics to VLMs, we provide a comprehensive BSA evaluation benchmark, a methodological perspective for embodied AI development, and a cognitive science-informed roadmap for achieving human-like spatial intelligence.

Weichen Zhang, Chen Gao, Shiquan Yu, Ruiying Peng, Baining Zhao, Qian Zhang, Jinqiang Cui, Xinlei Chen, Yong Li. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Baining Zhao, Jianjie Fang, Zichao Dai, Ziyou Wang, Jirong Zha, Weichen Zhang, Chen Gao, Yue Wang, Jinqiang Cui, Xinlei Chen, Yong Li. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

How creative is HCI research?Although creativity has been a notable theme in HCI, the landscape of the creativity of HCI research itself remains unclear.In this paper, we address this by measuring the disruptiveness of HCI research, one important dimension distinguishing the level of creativity, through a large-scale datadriven bibliometric analysis.By quantitatively tracing its evolution over the past 40 years, we find that the disruptiveness of HCI is decreasing sharply, even at a faster speed than the global average across all fields.We characterize the patterns shown by the themes, knowledge use, and authorship of disruptive papers in HCI, and identify how they associate with disruptiveness, e.g., the positive relationship between author freshness and disruptiveness.Based on our results, we discuss practical implications to improve and secure disruptiveness and creativity in HCI.

City-scale traffic signal control (TSC) involves thousands of heterogeneous intersections with varying topologies, making cooperative decision-making across intersections particularly challenging. Given the prohibitive computational cost of learning individual policies for each intersection, some researchers explore learning a universal policy to control each intersection in a decentralized manner, where the key challenge is to construct a universal representation method for heterogeneous intersections. However, existing methods are limited to universally representing information of heterogeneous ego intersections, neglecting the essential representation of influence from their heterogeneous neighbors. Universally incorporating neighborhood information is nontrivial due to the intrinsic complexity of traffic flow interactions, as well as the challenge of modeling collective influences from neighbor intersections. To address these challenges, we propose CityLight, which learns a universal policy based on representations obtained with two major modules: a Neighbor Influence Encoder to explicitly model neighbor's influence with specified traffic flow relation and connectivity to the ego intersection; a Neighbor Influence Aggregator to attentively aggregate the influence of neighbors based on their mutual competitive relations. Extensive experiments on five city-scale datasets, ranging from 97 to 13,952 intersections, confirm the efficacy of CityLight, with an average throughput improvement of 11.68% and a lift of 22.59% for generalization. Our codes and datasets are released: https://github.com/tsinghua-fib-lab/CityLight.

Accurate modeling and control of response length is essential for optimizing large language model (LLM) deployment, impacting computational efficiency, user experience, and system reliability.We develop a statistical framework based on extreme value theory, analyzing 14,301 GPT-4o responses across temperature settings and prompting strategies, with cross-validation on Qwen and DeepSeek architectures.Our analysis reveals that response lengths follow Weibull-type generalized extreme value (GEV) distributions, exhibiting heavier tails under stochastic generation conditions.The key contributions include:(1) a novel GEV-generalized Pareto (GPD) hybrid model that achieves superior tail fit (R 2 CDF = 0.9993 vs standalone GEV's 0.998) while preserving architectural generalizability;(2) quantitative characterization of prompt anchoring effects, showing reduced dispersion but increased outlier propensity under randomization; and (3) identification of temperaturedependent response patterns that remain consistent across architectures, where higher temperatures amplify length variability while maintaining the underlying extreme-value mechanisms.The proposed hybrid model's adaptive threshold selection enables precise verbosity control in production systems, regardless of the specific LLM architecture employed.These findings provide both theoretical insights into LLM generation patterns and practical tools for response length optimization.

Mengzhu Liu, Zhengqiu Zhu, Chuan Ai, Chen Gao, Xinghong Li, Lingnan He, Kaisheng Lai, Yingfeng Chen, Xin Lu, Yong Li, Quanjun Yin. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Yong Zhao, Kai Xu, Zhengqiu Zhu, Yue Hu, Zhiheng Zheng, Yingfeng Chen, Yatai Ji, Chen Gao, Yong Li, Jincai Huang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

User mobility trajectories and mobile traffic data are crucial for diverse applications yet challenging to obtain due to privacy and cost constraints, thereby making realistic data simulation essential. Although trajectories and mobile traffic are inherently coupled, most existing studies model them separately, limiting the capture of cross-modal dynamics. In this paper, we propose MSTDiff, a Multi-Scale Diffusion Transformer for joint simulation of mobile traffic and user trajectories. First, MSTDiff applies discrete wavelet transforms for multi-resolution traffic decomposition. Second, it uses a hybrid denoising network to process continuous traffic volumes and discrete location sequences. A transition mechanism based on urban knowledge graph embedding similarity is designed to guide semantically informed trajectory generation. Finally, a multi-scale Transformer with cross-attention captures dependencies between trajectories and traffic. Experiments show that MSTDiff surpasses state-of-the-art baselines, reducing Jensen-Shannon divergence (JSD) across key statistical metrics by over 25%. The source code is available at:https://github.com/tsinghua-fib-lab/MSTDiff.

As urban traffic networks grow more complex, seamless interaction between vehicles and infrastructure is critical, motivating Vehicle-to-Everything (V2X)-enabled intelligent transportation systems. Since vehicles are the main transport agents and traffic signals a key infrastructure component, jointly optimizing navigation and signal control is essential for sustainable V2X systems. However, existing methods often ignore long-range dependencies in road networks and lack effective large-scale vehicle coordination, limiting their ability to manage complex flows. To address this, we propose FCV2X-Net, a unified framework that enhances foresight and co-ordination in navigation and control. It consists of: (1) a Bayesian Graph Convolutional Network (BGCN)-based module with adaptive adjacency for modeling implicit long-range correlations; (2) a mean field-based intention propagation mechanism for scalable vehicle coordination; and (3) an intention-aware signal control module that adapts to aggregated vehicle intentions. Experiments on large-scale scenarios with 50 intersections show that FCV2X-Net increases vehicle throughput by 7.6% and reduces travel time by 7.2%, demonstrating its effectiveness for sustainable urban mobility. Codes and datasets are available at: https://github.com/JinweiZzz/FCV2X-Net.

Mobile traffic generation helps analysts predict network performance and synthesize high-fidelity traffic data based on environmental factors, supporting optimization and planning in 5G networks, such as base station sleep management and digital twins. However, existing methods mainly explore spatio-temporal (ST) relationships implicitly and lack explicit modeling of regional features. In this paper, we introduce a Regional Features Enhanced Diffusion Model (Re-Diff) to explicitly models regional features for accurate mobile traffic generation. We integrate an average mobile traffic predictor into the diffusion model’s denoising network. By using POI and AOI distributions, we establish relationships between the environment and average network traffic usage, thereby explicitly representing regional features. We then utilize a cross-attention mechanism to actively explore the dependencies at different scales between mobile traffic’s periodic characteristics and regional features, further improving the generation accuracy of mobile traffic. We validate Re-Diff on two real-world datasets, showing a 9.20% improvement in generation accuracy over current baselines. More importantly, the model’s transferability across different cities improves by over 14.57%, which highlights the importance of explicitly modeling the relationship between traffic and the environment. This capability helps understand the universal correlations between POI, AOI, and mobile traffic in different regions, enhancing the model’s generalizability. Our code is now available at https://github.com/tsinghua-fib-lab/Re-Diff.

Energy landscapes play a crucial role in shaping dynamics of many real-world complex systems. System evolution is often modeled as particles moving on a landscape under the combined effect of energy-driven drift and noise-induced diffusion, where the energy governs the long-term motion of the particles. Estimating the energy landscape of a system has been a longstanding interdisciplinary challenge, hindered by the high operational costs or the difficulty of obtaining supervisory signals. Therefore, the question of how to infer the energy landscape in the absence of true energy values is critical. In this paper, we propose a physics-informed self-supervised learning method to learn the energy landscape from the evolution trajectories of the system. It first maps the system state from the observation space to a discrete landscape space by an adaptive codebook, and then explicitly integrates energy into the graph neural Fokker-Planck equation, enabling the joint learning of energy estimation and evolution prediction. Experimental results across interdisciplinary systems demonstrate that our estimated energy has a correlation coefficient above 0.9 with the ground truth, and evolution prediction accuracy exceeds the baseline by an average of 17.65\%. The code is available at https://github.com/tsinghua-fib-lab/PESLA.

Commuting Origin-Destination~(OD) flows are critical inputs for urban planning and transportation, providing crucial information about the population residing in one region and working in another within an interested area. Due to the high cost of data collection, researchers have developed physical and computational models to generate commuting OD flows using readily available urban attributes, such as sociodemographics and points of interest, for cities lacking historical OD flows \textemdash commuting OD flow generation. Existing works developed models based on different techniques and achieved improvement on different datasets with different evaluation metrics, which hinderes establishing a unified standard for comparing model performance. To bridge this gap, we introduce a large-scale dataset containing commuting OD flows for 3,333 areas including a wide range of urban environments around the United States. Based on that, we benchmark widely used models for commuting OD flow generation. We surprisingly find that the network-based generative models achieve the optimal performance in terms of both precision and generalization ability, which may inspire new research directions of graph generative modeling in this field. The dataset and benchmark are available at https://anonymous.4open.science/r/CommutingODGen-Dataset-0D4C/.

Recent advancements in Large Language Models (LLMs) have led to a rapid growth of agentic systems capable of handling a wide range of complex tasks. However, current research largely relies on manual, task-specific design, limiting their adaptability to novel tasks. In this paper, we introduce a new research problem: Modularized LLM Agent Search (MoLAS). We propose a modular design space that abstracts existing LLM agent designs into four fundamental modules with uniform IO interface: Planning, Reasoning, Tool Use, and Memory. Building on this design space, we present a novel LLM agent search framework called AgentSquare, which introduces two core mechanisms, i.e., module evolution and recombination, to efficiently search for optimized LLM agents. To further accelerate the process, we design a performance predictor that uses in-context surrogate models to skip unpromising agent designs. Extensive experiments across six benchmarks, covering the diverse scenarios of web, embodied, tool use and game applications, show that AgentSquare substantially outperforms hand-crafted agents, achieving an average performance gain of 17.2% against best-known human designs. Moreover, AgentSquare can generate interpretable design insights, enabling a deeper understanding of agentic architecture and its impact on task performance. We believe that the modular design space and AgentSquare search framework offer a platform for fully exploiting the potential of prior successful designs and consolidate the collective efforts of research community. Code repo is available at https://github.com/tsinghua-fib-lab/AgentSquare.

Symbolic regression, a task discovering the formula best fitting the given data, is typically based on the heuristical search. These methods usually update candidate formulas to obtain new ones with lower prediction errors iteratively. However, since formulas with similar function shapes may have completely different symbolic forms, the prediction error does not decrease monotonously as the search approaches the target formula, causing the low recovery rate of existing methods. To solve this problem, we propose a novel search objective based on the minimum description length, which reflects the distance from the target and decreases monotonically as the search approaches the correct form of the target formula. To estimate the minimum description length of any input data, we design a neural network, MDLformer, which enables robust and scalable estimation through large-scale training. With the MDLformer's output as the search objective, we implement a symbolic regression method, SR4MDL, that can effectively recover the correct mathematical form of the formula. Extensive experiments illustrate its excellent performance in recovering formulas from data. Our method successfully recovers around 50 formulas across two benchmark datasets comprising 133 problems, outperforming state-of-the-art methods by 43.92%. Experiments on 122 unseen black-box problems further demonstrate its generalization performance. We release our code at https://github.com/tsinghua-fib-lab/SR4MDL .

Chain-of-Thought (CoT) technique has proven effective in improving the performance of large language models (LLMs) on complex reasoning tasks. However, the performance gains are inconsistent across different tasks, and the underlying mechanism remains a long-standing research question. In this work, we make a preliminary observation that the monotonicity of token probability distributions may be correlated with the gains achieved through CoT reasoning. Leveraging this insight, we propose two indicators based on the token probability distribution to assess CoT effectiveness across different tasks. By combining instance-level indicators with logistic regression model, we introduce Dynamic CoT, a method that dynamically select between CoT and direct answer. Furthermore, we extend Dynamic CoT to closed-source models by transferring decision strategies learned from open-source models. Our indicators for assessing CoT effectiveness achieve an accuracy of 89.2%, and Dynamic CoT reduces token consumption by more than 35% while maintaining high accuracy. Overall, our work offers a novel perspective on the underlying mechanisms of CoT reasoning and provides a framework for its more efficient deployment.

Training reinforcement learning (RL) agents requires extensive trials and errors, which becomes prohibitively time-consuming in systems with costly reward evaluations. To address this challenge, we propose adaptive reward modeling (AdaReMo) which accelerates RL training by decomposing the complicated reward function into multiple localized fast reward models approximating direct reward evaluation with neural networks. These models dynamically adapt to the agent’s evolving policy by fitting the currently explored subspace with the latest trajectories, ensuring accurate reward estimation throughout the entire training process while significantly reducing computational overhead. We empirically show that AdaReMo not only achieves over 1,000 times speedup but also improves the performance by 14.6% over state-of-the-art approaches across three expensive-to-evaluate systems---molecular generation, epidemic control, and spatial planning. Code and data for the project are provided at https://github.com/tsinghua-fib-lab/AdaReMo.

The pervasive use of short-video applications has raised concerns about their potential negative effects on users, particularly addiction. Existing research often relies on psychological questionnaires, which lack real-world behavioral data, limiting scalability and analytical depth. To address this, we assess the addiction status of short-video platform users using a standardized psychometric questionnaire, combined with platform behavioral data and interview responses to uncover features associated with addiction. Using feature-based modeling, we scale to a dataset of 10,111 addiction-labeled users and identify key indicators of addiction, including prolonged daily watch time, especially at night, and excessive video consumption, while also revealing that higher watch frequency is not fully correlated with addiction. Additionally, we find that addicted users tend to consume a narrower range of content, suggesting a filter bubble effect. Our large-scale analysis provides valuable insights for platform designers, policymakers, and mental health professionals seeking to promote healthier engagement and mitigate the risks of short-video addiction.

Online-to-offline (O2O) food delivery platforms have greatly expanded urban residents' access to a wide range of food options by allowing convenient ordering from distant food outlets. However, concerns persist regarding the nutritional quality of delivered food, particularly as the impact of O2O food delivery platforms on users’ healthy food remains unclear. This study leverages large-scale empirical data from a leading O2O delivery platform to comprehensively analyze online food choice behaviors and how they are influenced by the online exposure to fast food restaurants, i.e., online food environment. Our analyses reveal significant variations in food preferences across demographic groups and city sizes, where male, low-income, and younger users are more likely to order fast food via O2O platforms. Besides, we also perform a comparative analysis on the food exposure differences in offline and online environments, confirming that the extended service ranges of O2O platforms can create larger "cyber food swamps". Furthermore, regression analysis highlights that a higher ratio of fast food orders is associated with "cyber food swamps", areas characterized by a higher proportion of accessible fast food restaurants. A 10% increase in this proportion raises the probability of ordering fast food by 22.0%. Moreover, a quasi-natural experiment substantiates the long-term causal effect of online food environment changes on healthy food choices. These findings underscore the need for O2O food delivery platforms to address the health implications of online food choice exposure, offering critical insights for stakeholders aiming to improve dietary health among urban populations.

Accurate prediction of mobile traffic,i.e., network traffic from cellular base stations, is crucial for optimizing network performance and supporting urban development. However, the non-stationary nature of mobile traffic, driven by human activity and environmental changes, leads to both regular patterns and abrupt variations. Diffusion models excel in capturing such complex temporal dynamics due to their ability to capture the inherent uncertainties. Most existing approaches prioritize designing novel denoising networks but often neglect the critical role of noise itself, potentially leading to sub-optimal performance. In this paper, we introduce a novel perspective by emphasizing the role of noise in the denoising process. Our analysis reveals that noise fundamentally shapes mobile traffic predictions, exhibiting distinct and consistent patterns. We propose NPDiff, a framework that decomposes noise into prior and residual components, with the prior derived from data dynamics, enhancing the model's ability to capture both regular and abrupt variations. NPDiff can seamlessly integrate with various diffusion-based prediction models, delivering predictions that are effective, efficient, and robust. Extensive experiments demonstrate that it achieves superior performance with an improvement over 30%, offering a new perspective on leveraging diffusion models in this domain. We provide code and data at https://github.com/tsinghua-fib-lab/NPDiff.

Accurately estimating high-resolution carbon emissions is crucial for effective emission governance and mitigation planning. While conventional methods for precise carbon accounting are hindered by substantial data collection efforts, the rise of open data and advanced learning techniques offers a promising solution. Once an open data-based prediction model is developed and trained, it can easily infer emissions for new areas based on available open data. To address this, we incorporate two modalities of open data, satellite images and point-of-interest (POI) data, to predict high-resolution urban carbon emissions, with satellite images providing macroscopic and static and POI data offering fine-grained and relatively dynamic functionality information. However, estimating high-resolution carbon emissions presents two significant challenges: the intertwined and implicit effects of various functionalities on carbon emissions, and the complex spatial contiguity correlations that give rise to the agglomeration effect. Our model, OpenCarbon, features two major designs that target the challenges: a cross-modality information extraction and fusion module to extract complementary functionality information from two modules and model their interactions, and a neighborhood-informed aggregation module to capture the spatial contiguity correlations. Extensive experiments demonstrate our model's superiority, with a significant performance gain of 26.6% on R2. Further generalizability tests and case studies also show OpenCarbon's capacity to capture the intrinsic relation between urban functionalities and carbon emissions, validating its potential to empower efficient carbon governance and targeted carbon mitigation planning. Codes and data are available: https://github.com/JinweiZzz/OpenCarbon.

Effective decision-making on networks often relies on learning from graph-structured data, where Graph Neural Networks (GNNs) play a central role, but they take efforts to configure and tune. In this demo, we propose LLMNet, showing how to design GNN automated through Large Language Models. Our system develops a set of agents that construct graph-related knowlege bases and then leverages Retrieval-Augmented Generation (RAG) to support automated configuration and refinement of GNN models through a knowledge-guided evolution process. These agents, equipped with specialized knowledge bases, extract insights into tasks and graph structures by interacting with the knowledge bases.Empirical results show LLMNet excels in twelve datasets across three graph learning tasks, validating its effectiveness of GNN model designing.

As large language models (LLMs) continue to advance and gain widespread use, establishing systematic and reliable evaluation methodologies for LLMs and vision-language models (VLMs) has become essential to ensure their real-world effectiveness and reliability. There have been some early explorations about the usability of LLMs for limited urban tasks, but a systematic and scalable evaluation benchmark is still lacking. The challenge in constructing a systematic evaluation benchmark for urban research lies in the diversity of urban data, the complexity of application scenarios and the highly dynamic nature of the urban environment. In this paper, we design CityBench, an interactive simulator based evaluation platform, as the first systematic benchmark for evaluating the capabilities of LLMs for diverse tasks in urban research. First, we build CityData to integrate the diverse urban data and CitySimu to simulate fine-grained urban dynamics. Based on CityData and CitySimu, we design 8 representative urban tasks in 2 categories of perception-understanding and decision-making as the CityBench. With extensive results from 30 well-known LLMs and VLMs in 13 cities around the world, we find that advanced LLMs and VLMs can achieve competitive performance in diverse urban tasks requiring commonsense and semantic understanding abilities, e.g., understanding the human dynamics and semantic inference of urban images. Meanwhile, they fail to solve the challenging urban tasks requiring professional knowledge and high-level numerical abilities, e.g., geospatial prediction and traffic control task. These findings provide critical insights for the effective utilization and further development of LLMs to advance urban-related tasks and research in the future.

Predicting the dynamics of complex systems is crucial for various scientific and engineering applications. The accuracy of predictions depends on the model's ability to capture the intrinsic dynamics. While existing methods capture key dynamics by encoding a low-dimensional latent space, they overlook the inherent multiscale structure of complex systems, making it difficult to accurately predict complex spatiotemporal evolution. Therefore, we propose a Multiscale Diffusion Prediction Network (MDPNet) that leverages the multiscale structure of complex systems to discover the latent space of intrinsic dynamics. First, we encode multiscale features through a multiscale diffusion autoencoder to guide the diffusion model for reliable reconstruction. Then, we introduce an attention-based graph neural ordinary differential equation to model the co-evolution across different scales. Extensive evaluations on representative systems demonstrate that the proposed method achieves an average prediction error reduction of 53.23% compared to baselines, while also exhibiting superior robustness and generalization.

Large language models(LLMs), with their powerful language generation and reasoning capabilities, have already achieved notable success in many domains, e.g., math and code generation. However, they often fall short when tackling real-life geospatial tasks within urban environments. This limitation stems from a lack of physical world knowledge and relevant data during training. To address this gap, we propose CityGPT, a systematic framework designed to enhance LLMs' understanding of urban space and improve their ability to solve the related urban tasks by integrating a city-scale 'world model' into the model. Firstly, we construct a diverse instruction tuning dataset, CityInstruction, for injecting urban knowledge into LLMs and effectively boosting their spatial reasoning capabilities. Using a combination of CityInstruction and open source general instruction data, we introduce a novel and easy-to-use self-weighted fine-tuning method (SWFT) to train various LLMs (including ChatGLM3-6B, Llama3-8B, and Qwen2.5-7B) to enhance their urban spatial capabilities without compromising, or even improving, their general abilities. Finally, to validate the effectiveness of our proposed framework, we develop a comprehensive text-based spatial benchmark CityEval for evaluating the performance of LLMs across a wide range of urban scenarios and geospatial tasks. Extensive evaluation results demonstrate that smaller LLMs trained with CityInstruction by SWFT method can achieve performance that is competitive with, and in some cases superior to, proprietary LLMs when assessed using CityEval. Our work highlights the potential for integrating spatial knowledge into LLMs, thereby expanding their spatial cognition abilities and applicability to the real-world physical environments. The dataset, benchmark, and source code are open-sourced and can be accessed through https://github.com/tsinghua-fib-lab/CityGPT.

Mobile traffic forecasting allows operators to anticipate network dynamics and performance in advance, offering substantial potential for enhancing service quality and improving user experience. It involves multiple tasks, including long-term prediction, short-term prediction, and generation tasks that do not rely on historical data. By leveraging the different types of mobile network data generated from these tasks, operators can perform a variety of network optimizations and planning activities, such as base station (BS) deployment, resource allocation, energy optimization, etc. However, existing models are often designed for specific tasks and trained with specialized data, and there is a lack of universal models for traffic forecasting across different urban environments. In this paper, we propose a Universal model for Mobile traffic forecasting (UoMo), aiming to handle diverse forecasting tasks of short/long-term predictions and distribution generation across multiple cities to support network planning and optimization. UoMo combines diffusion models and transformers, where various spatio-temporal masks are proposed to enable UoMo to learn intrinsic features of different tasks, and a contrastive learning strategy is developed to capture the correlations between mobile traffic and urban contexts, thereby improving its transfer learning capability. Extensive evaluations on 9 real-world datasets demonstrate that UoMo outperforms current models in various forecasting tasks and zero/few-shot learning. It shows an average accuracy improvement of 27.85%, 18.57%, and 15.6% in long-term prediction, short-term prediction, and generation tasks, respectively, showcasing its strong forecasting capability. We deploy UoMo on China Mobile's JiuTian platform, leveraging the predicted mobile data to optimize live networks. This optimization includes BS deployment, resulting in a 25.3% increase in served users, and BS sleep control, which reduces equipment depreciation by 40.7%. The source code is available online: https://github.com/tsinghua-fib-lab/UoMo.

Large language models (LLMs) have exhibited remarkable capabilities and achieved significant breakthroughs across various domains, leading to their widespread adoption in recent years. Building on this progress, we investigate their potential in the realm of local life services. In this study, we establish a comprehensive benchmark and systematically evaluate the performance of diverse LLMs across a wide range of tasks relevant to local life services. To further enhance their effectiveness, we explore two key approaches: model fine-tuning and agent-based workflows. Our findings reveal that even a relatively compact 7B model can attain performance levels comparable to a much larger 72B model, effectively balancing inference cost and model capability. This optimization greatly enhances the feasibility and efficiency of deploying LLMs in real-world online services, making them more practical and accessible for local life applications. Available resources are at https://github.com/tsinghua-fib-lab/LocalEval.

Predicting human mobility is crucial for urban planning, traffic control, and emergency response. Mobility behaviors can be categorized into individual and collective, and these behaviors are recorded by diverse mobility data, such as individual trajectory and crowd flow. As different modalities of mobility data, individual trajectory and crowd flow have a close coupling relationship. Crowd flows originate from the bottom-up aggregation of individual trajectories, while the constraints imposed by crowd flows shape these individual trajectories. Existing mobility prediction methods are limited to single tasks due to modal gaps between individual trajectory and crowd flow. In this work, we aim to unify mobility prediction to break through the limitations of task-specific models. We propose a universal human mobility prediction model (named UniMob), which can be applied to both individual trajectory and crowd flow. UniMob leverages a multi-view mobility tokenizer that transforms both trajectory and flow data into spatiotemporal tokens, facilitating unified sequential modeling through a diffusion transformer architecture. To bridge the gap between the different characteristics of these two data modalities, we implement a novel bidirectional individual and collective alignment mechanism. This mechanism enables learning common spatiotemporal patterns from different mobility data, facilitating mutual enhancement of both trajectory and flow predictions. Extensive experiments on real-world datasets validate the superiority of our model over state-of-the-art baselines in trajectory and flow prediction. Especially in noisy and scarce data scenarios, our model achieves the highest performance improvement of more than 14% and 25% in MAPE and Accuracy@5. The codes are available online: https://github.com/tsinghua-fib-lab/UniMob.

Graph-based Cognitive Diagnosis (CD) has attracted much research interest due to its strong ability on inferring students' proficiency levels on knowledge concepts. While graph-based CD models have demonstrated remarkable performance, we contend that they still cannot achieve optimal performance due to the neglect of edge heterogeneity and uncertainty. Edges involve both correct and incorrect response logs, indicating heterogeneity. Meanwhile, a response log can have uncertain semantic meanings, e.g., a correct log can indicate true mastery or fortunate guessing, and a wrong log can indicate a lack of understanding or a careless mistake. In this paper, we propose an Informative Semantic-aware Graph-based Cognitive Diagnosis model (ISG-CD), which focuses on how to utilize the heterogeneous graph in CD and minimize effects of uncertain edges. Specifically, to explore heterogeneity, we propose a semantic-aware graph neural networks based CD model. To minimize effects of edge uncertainty, we propose an Informative Edge Differentiation layer from an information bottleneck perspective, which suggests keeping a minimal yet sufficient reliable graph for CD in an unsupervised way. We formulate this process as maximizing mutual information between the reliable graph and response logs, while minimizing mutual information between the reliable graph and the original graph. After that, we prove that mutual information maximization can be theoretically converted to the classic binary cross entropy loss function, while minimizing mutual information can be realized by the Hilbert-Schmidt Independence Criterion.Finally, we adopt an alternating training strategy for optimizing learnable parameters of both the semantic-aware graph neural networks based CD model and the edge differentiation layer. Extensive experiments on three real-world datasets have demonstrated the effectiveness of ISG-CD.

Spatial reasoning is a fundamental capability of multimodal large language models (MLLMs), yet their performance in open aerial environments remains underexplored. In this work, we present Open3D-VQA, a novel benchmark for evaluating MLLMs' ability to reason about complex spatial relationships from an aerial perspective. The benchmark comprises 73k QA pairs across seven general spatial reasoning tasks, offered in multiple-choice, true/false, and short-answer formats, and supports both visual and point cloud modalities. The questions are automatically generated from spatial relations extracted from both real-world and simulated aerial scenes. Evaluation on 13 popular MLLMs reveals that: 1) Models are generally better at answering questions about relative spatial relations than absolute distances, 2) 3D LLMs fail to demonstrate significant advantages over 2D LLMs, and 3) Fine-tuning solely on the simulated dataset can significantly improve the model's spatial reasoning performance in real-world scenarios. The benchmark, generation pipeline, and evaluation toolkit are released on this page.

How to enable agents to predict the outcomes of their own motion intentions in three-dimensional space has been a fundamental problem in embodied intelligence. To explore general spatial imagination capability, we present AirScape, the first world model designed for six-degree-of-freedom aerial agents. AirScape predicts future observation sequences based on current visual inputs and motion intentions. Specifically, we construct a dataset for aerial world model training and testing, which consists of 11k video-intention pairs. This dataset includes first-person-view videos capturing diverse drone actions across a wide range of scenarios, with over 1,000 hours spent annotating the corresponding motion intentions. Then we develop a two-phase schedule to train a foundation model-initially devoid of embodied spatial knowledge-into a world model that is controllable by motion intentions and adheres to physical spatio-temporal constraints. Experimental results demonstrate that AirScape significantly outperforms existing foundation models in 3D spatial imagination capabilities, especially with over a 50% improvement in metrics reflecting motion alignment. The project is available at: https://embodiedcity.github.io/AirScape/.

Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This paper introduces Embodied-R, a collaborative framework combining large-scale Vision-Language Models (VLMs) for perception and small-scale Language Models (LMs) for reasoning. Using Reinforcement Learning (RL) with a novel reward system considering think-answer logical consistency, the model achieves slow-thinking capabilities with limited computational resources. After training on only 5k embodied video samples, Embodied-R with a 3B LM matches state-of-the-art multimodal reasoning models (OpenAI-o1, Gemini-2.5-pro) on both in-distribution and out-of-distribution embodied spatial reasoning tasks. Embodied-R also exhibits emergent thinking patterns such as systematic analysis and contextual integration. We further explore research questions including response length, training on VLM, strategies for reward design, and differences in model generalization after SFT (Supervised Fine-Tuning) and RL training. The project page is available at: https://embodiedcity.github.io/Embodied-R/.

Jie Feng, Yuwei Du, Jie Zhao, Yong Li. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Predicting the behavior of complex systems is critical in many scientific and engineering domains, and hinges on the model’s ability to capture their underlying dynamics. Existing methods encode the intrinsic dynamics of high-dimensional observations through latent representations and predict autoregressively. However, these latent representations lose the inherent spatial structure of spatiotemporal dynamics, leading to the predictor's inability to effectively model spatial interactions and neglect emerging dynamics during long-term prediction. In this work, we propose SparseDiff, introducing a test-time adaptation strategy to dynamically update the encoding scheme to accommodate emergent spatiotemporal structures during the long-term evolution of the system. Specifically, we first design a codebook-based sparse encoder, which coarsens the continuous spatial domain into a sparse graph topology. Then, we employ a graph neural ordinary differential equation to model the dynamics and guide a diffusion decoder for reconstruction. SparseDiff autoregressively predicts the spatiotemporal evolution and adjust the sparse topological structure to adapt to emergent spatiotemporal patterns by adaptive re-encoding. Extensive evaluations on representative systems demonstrate that SparseDiff achieves an average prediction error reduction of 49.99\% compared to baselines, requiring only 1\% of the spatial resolution.

Trajectory modeling, which includes research on trajectory data pattern mining and future prediction, has widespread applications in areas such as life services, urban transportation, and public administration. Numerous methods have been proposed to address specific problems within trajectory modeling. However, the heterogeneity of data and the diversity of trajectory tasks make effective and reliable trajectory modeling an important yet highly challenging endeavor, even for domain experts. In this paper, we propose TrajAgent, a agent framework powered by large language models (LLMs), designed to facilitate robust and efficient trajectory modeling through automation modeling. This framework leverages and optimizes diverse specialized models to address various trajectory modeling tasks across different datasets effectively. In TrajAgent, we first develop UniEnv, an execution environment with a unified data and model interface, to support the execution and training of various models. Building on UniEnv, we introduce an agentic workflow designed for automatic trajectory modeling across various trajectory tasks and data. Furthermore, we introduce collaborative learning schema between LLM-based agents and small speciallized models, to enhance the performance of the whole framework effectively. Extensive experiments on four tasks using four real-world datasets demonstrate the effectiveness of TrajAgent in automated trajectory modeling, achieving a performance improvement of 2.38%-69.91% over baseline methods. The codes and data can be accessed via https://github.com/tsinghua-fib-lab/TrajAgent.

Policy exploration is critical in reinforcement learning (RL), where existing approaches include $\epsilon$-greedy, Gaussian process, etc. However, these approaches utilize preset stochastic processes and are indiscriminately applied in all kinds of RL tasks without considering task-specific features that influence policy exploration. Moreover, during RL training, the evolution of such stochastic processes is rigid, which typically only incorporates a decay in the variance, failing to adjust flexibly according to the agent's real-time learning status. Inspired by the analyzing and reasoning capability of large language models (LLMs), we design **LLM-Explorer** to adaptively generate task-specific exploration strategies with LLMs, enhancing the policy exploration in RL. In our design, we sample the learning trajectory of the agent during the RL training in a given task and prompt the LLM to analyze the agent's current policy learning status and then generate a probability distribution for future policy exploration. Updating the probability distribution periodically, we derive a stochastic process specialized for the particular task and dynamically adjusted to adapt to the learning process. Our design is a plug-in module compatible with various widely applied RL algorithms, including the DQN series, DDPG, TD3, and any possible variants developed based on them. Through extensive experiments on the Atari and MuJoCo benchmarks, we demonstrate LLM-Explorer's capability to enhance RL policy exploration, achieving an average performance improvement up to 37.27%. Our code is open-source at https://github.com/tsinghua-fib-lab/LLM-Explorer for reproducibility.

Large Vision-Language Models (LVLMs) have shown impressive performance across multi-modal tasks by encoding images into thousands of tokens. However, the large number of image tokens results in significant computational overhead, and the use of dynamic high-resolution inputs further increases this burden. Previous approaches have attempted to reduce the number of image tokens through token pruning, typically by selecting tokens based on attention scores or image token diversity. Through empirical studies, we observe that existing methods often overlook the joint impact of pruning on both the current layer's output (local) and the outputs of subsequent layers (global), leading to suboptimal pruning decisions. To address this challenge, we propose Balanced Token Pruning (BTP), a plug-and-play method for pruning vision tokens. Specifically, our method utilizes a small calibration set to divide the pruning process into multiple stages. In the early stages, our method emphasizes the impact of pruning on subsequent layers, whereas in the deeper stages, the focus shifts toward preserving the consistency of local outputs. Extensive experiments across various LVLMs demonstrate the broad effectiveness of our approach on multiple benchmarks. Our method achieves a 78\% compression rate while preserving 96.7\% of the original models' performance on average. Our code is available at https://github.com/EmbodiedCity/NeurIPS2025-Balanced-Token-Pruning.

Commuting Origin-destination (OD) flows, capturing daily population mobility of citizens, are vital for sustainable development across cities around the world. However, it is challenging to obtain the data due to the high cost of travel surveys and privacy concerns. Surprisingly, we find that satellite imagery, publicly available across the globe, contains rich urban semantic signals to support high-quality OD flow generation, with over 98\% expressiveness of traditional multisource hard-to-collect urban sociodemographic, economics, land use, and point of interest data. This inspires us to design a novel data generator, GlODGen (Global-scale OriginDestination Flow Generator), which can generate OD flow data for any cities of interest around the world. Specifically, GlODGen first leverages Vision-Language Geo-Foundation Models to extract urban semantic signals related to human mobility from satellite imagery. These features are then combined with population data to form region-level representations, which are used to generate OD flows via graph diffusion models. Extensive experiments on 4 continents and 6 representative cities show that GlODGen has great generalizability across diverse urban environments on different continents and can generate OD flow data for global cities highly consistent with real-world mobility data. We implement GlODGen as an automated tool, seamlessly integrating data acquisition and curation, urban semantic feature extraction, and OD flow generation together. It has been released at https://github.com/tsinghua-fib-lab/generate-od-pubtools.

The emergence of agentic recommender systems powered by Large Language Models (LLMs) represents a paradigm shift in personalized recommendations, leveraging LLMs’ advanced reasoning and role-playing capabilities to enable autonomous, adaptive decision-making. Unlike traditional recommendation approaches, agentic recommender systems can dynamically gather and interpret user-item interactions from complex environments, generating robust recommendation strategies that generalize across diverse scenarios. However, the field currently lacks standardized evaluation protocols to systematically assess these methods. To address this critical gap, we propose: (1) an interactive textual recommendation simulator incorporating rich user and item metadata and three typical evaluation scenarios (classic, evolving-interest, and cold-start recommendation tasks); (2) a unified modular framework for developing agentic recommender systems; and (3) the first comprehensive benchmark comparing over 10 classical and agentic recommendation methods. Our findings demonstrate the superiority of agentic systems and establish actionable design guidelines for their core components. The benchmark environment has been rigorously validated through an open challenge and remains publicly available with a maintained leaderboard at https://tsinghua-fib-lab.github.io/AgentSocietyChallenge/pages/overview.html. The benchmark is available at: https://huggingface.co/datasets/SGJQovo/AgentRecBench.

World models have become indispensable tools for embodied intelligence, serving as powerful simulators capable of generating realistic robotic videos while addressing critical data scarcity challenges. However, current embodied world models exhibit limited physical awareness, particularly in modeling 3D geometry and motion dynamics, resulting in unrealistic video generation for contact-rich robotic scenarios. In this paper, we present RoboScape, a unified physics-informed world model that jointly learns RGB video generation and physics knowledge within an integrated framework. We introduce two key physics-informed joint training tasks: temporal depth prediction that enhances 3D geometric consistency in video rendering, and keypoint dynamics learning that implicitly encodes physical properties (e.g., object shape and material characteristics) while improving complex motion modeling. Extensive experiments demonstrate that RoboScape generates videos with superior visual fidelity and physical plausibility across diverse robotic scenarios. We further validate its practical utility through downstream applications including robotic policy training with generated data and policy evaluation. Our work provides new insights for building efficient physics-informed world models to advance embodied intelligence research. Our code and demos are available at: https://github.com/tsinghua-fib-lab/RoboScape.

The quality of the video dataset (image quality, resolution, and fine-grained caption) greatly influences the performance of the video generation model. %The growing demand for video applications sets higher requirements for high-quality video generation models. %For example, the generation of movie-level Ultra-High Definition (UHD) videos and the creation of 4K short video content. %However, the existing public datasets cannot support related research and applications. %In this paper, we first propose a high-quality open-sourced UHD-4K (22.4\% of which are 8K) text-to-video dataset named UltraVideo, which contains a wide range of topics (more than 100 kinds), and each video has 9 structured captions with one summarized caption (average of 824 words). %Specifically, we carefully design a highly automated curation process with four stages to obtain the final high-quality dataset: i) collection of diverse and high-quality video clips. ii statistical data filtering. iii) model-based data purification. iv) generation of comprehensive, structured captions. %In addition, we expand Wan to UltraWan-1K/-4K, which can natively generate high-quality 1K/4K videos with more consistent text controllability, demonstrating the effectiveness of our data curation.%We believe that this work can make a significant contribution to future research on UHD video generation. UltraVideo dataset and UltraWan models are available at https://xzc-zju.github.io/projects/UltraVideo.

The urban environment is characterized by complex spatio-temporal dynamics arising from diverse human activities and interactions. Effectively modeling these dynamics is essential for understanding and optimizing urban systems. In this work, we introduce UrbanDiT, a foundation model for open-world urban spatio-temporal learning that successfully scales up diffusion transformers in this field. UrbanDiT pioneers a unified model that integrates diverse data sources and types while learning universal spatio-temporal patterns across different cities and scenarios. This allows the model to unify both multi-data and multi-task learning, and effectively support a wide range of spatio-temporal applications. Its key innovation lies in the elaborated prompt learning framework, which adaptively generates both data-driven and task-specific prompts, guiding the model to deliver superior performance across various urban applications. UrbanDiT offers three advantages: 1) It unifies diverse data types, such as grid-based and graph-based data, into a sequential format; 2) With task-specific prompts, it supports a wide range of tasks, including bi-directional spatio-temporal prediction, temporal interpolation, spatial extrapolation, and spatio-temporal imputation; and 3) It generalizes effectively to open-world scenarios, with its powerful zero-shot capabilities outperforming nearly all baselines with training data. UrbanDiT sets up a new benchmark for foundation models in the urban spatio-temporal domain. Code and datasets are publicly available at \url{https://github.com/tsinghua-fib-lab/UrbanDiT}.

Dynamic link prediction aims to predict the future links on dynamic graphs, which can be applied to wide scenarios such as recommender systems and social networks on the World Wide Web. Existing methods mainly (1) focus on the in-graph learning, which cannot generalize to graphs unobserved during training; or (2) achieve the cross-graph predictions in a many-many mechanism by training on multiple graphs across various domains, which results in a large computational cost. In this paper, we propose a cross-graph dynamic link predictor named CrossDyG, which achieves the cross-graph transferability in a one-many mechanism which trains on one single source graph and test on different target graphs. Specifically, we provide causal and empirical analysis on the structural bias caused by the graph-specific structural characteristics in cross-graph predictions. Then, we conduct deconfounded training to learn the universal network evolution pattern from one single source graph during training. Finally, we apply the causal intervention to leverage the graph-specific structural characteristics of each target graph during inference. Extensive experiments conducted on three benchmark data of dynamic graphs demonstrate that CrossDyG outperforms the state-of-the-art baselines by up to 11.01% and 17.02% in terms of AP and AUC, respectively. In addition, the improvements are especially significant when training on small source graphs.

Recent advances in the large language models (LLM) have empowered traditional bots to gain human-level intelligence and exhibit human-like social behaviors, giving rise to a new form of LLM-driven social agents. However, the inherent limitations in LLMs could potentially result in politically biased behaviors of these agents, posing unexpected risks to human society. While great efforts have been made to examine political bias and related concerns in traditional bots and LLMs, little is known about the existence, unique characteristics, underlying origins, and potential mitigation strategies of this bias in LLM-driven social agents. To address this gap, we systematically assess political bias in LLM-driven social agents, by examining how it emerges as these agents self-reflect, communicate, and understand others during social interactions. Through designing and implementing social experiments, we discover that this bias consistently manifests in the social behaviors of agents driven by diverse LLMs, across nine key political topics. Inspired by the social learning theory, we propose to mitigate political bias by guiding these agents to emulate how humans learn to behave. By incorporating self-regulated and role-model learning processes, we reduce their political bias by 4.89% to 51.26% across diverse LLMs and topics, demonstrating the effectiveness and generalizability of the proposed strategy. This study not only advances the understanding of political bias in emerging LLM-driven agents, but also offers insights into harnessing social bots for social good.

With global urbanization, the focus on sustainable cities has largely grown, driving research into equity, resilience, and urban planning, which often relies on mobility data. The rise of web-based apps and mobile devices has provided valuable user data for mobility-related research. However, real-world mobility data is costly and raises privacy concerns. To protect privacy while retaining key features of real-world movement, the demand for synthetic data has steadily increased. Recent advances in diffusion models have shown great potential for mobility trajectory generation due to their ability to model randomness and uncertainty. However, existing approaches often directly apply identically distributed (i.i.d.) noise sampling from image generation techniques, which fail to account for the spatiotemporal correlations and social interactions that shape urban mobility patterns. In this paper, we propose CoDiffMob, a diffusion model for urban mobility generation with collaborative noise priors, we emphasize the critical role of noise in diffusion models for generating mobility data. By leveraging both individual movement characteristics and population-wide dynamics, we construct novel collaborative noise priors that provide richer and more informative guidance throughout the generation process. Extensive experiments demonstrate the superiority of our method, with generated data accurately capturing both individual preferences and collective patterns, achieving an improvement of over 32%. Furthermore, it can effectively replace web-derived mobility data to better support downstream applications, while safeguarding user privacy and fostering a more secure and ethical web. This highlights its tremendous potential for applications in sustainable city-related research. The code and data are available at https://github.com/tsinghua-fib-lab/CoDiffMob.

The rapid pace of urbanization has led to unequal benefits for residents, creating significant inequality issues and discussions around Sustainable Development Goals 10 and 11. Accurate measurement of inequality within urban areas is essential for effective mitigation strategies. Traditional methods rely on survey-based census data, which are time-consuming and delayed, while some studies use coarse proxies like nighttime lights. However, these methods are limited by resolution and fail to capture fine-grained disparities within communities. To address this, we aim to leverage accessible urban imagery, which offers detailed visual features. Two key challenges must be addressed: 1) accurately perceiving micro-level inequalities within neighborhoods, and 2) ensuring that this perception is interpretable for policy guidance. To address these gaps, we propose UI-CoT, a framework that leverages the power of urban imagery-based visual language models in urban inequality perceiving, enhanced by Chain-of-Thought prompting to improve reasoning capabilities. We fine-tune a visual language model to predict three essential neighborhood inequality indicators: the income Gini coefficient, dominant race, and racial income ratio. Extensive experiments show that our model can effectively perceive micro-level inequalities, with the incorporation of Chain-of-Thought reasoning further improving the model's performance by 17.2%. This research offers valuable insights into addressing inequalities within urban environments and demonstrates the potential of web resources in empowering urban sustainable development. The code and data are available at https://github.com/tsinghua-fib-lab/UI-CoT.

In large-scale Internet of Things (IoT) networks, generating high-fidelity packet trace data (e.g., packet size, packet time interval) is crucial for developing more powerful and precise network analysis tools. The packet data facilitates improved monitoring, threat detection, and the design of tailored resource allocation strategies to enhance user experiences. However, due to the inherent variability of IoT services and the complex temporal dependencies between network packets, producing detailed packet trace data for multiple services remains a challenging task. In this paper, we propose PacketDiff, a novel diffusion model that generates network packet trace data for diverse services based on statistical network data (i.e., network flow data). We first design an IP graph to characterize and learn the preference relationships between different IoT devices in terms of service usage. Afterward, a classifier-free guidance denoising network that integrates network flow information is designed with dual-layer transformer architectures to enhance the controllability of the generation process. Unlike traditional methods, which often rely on the simple replication of statistical patterns within IoT traffic data and fail to account for the dynamic and varied nature of IoT networks, our approach offers a more robust and accurate solution. Extensive experiments conducted on two real-world IoT datasets demonstrate that PacketDiff closely approximates real network packet data, particularly concerning key characteristics such as average packet size and time interval, with improvements of 43.4% and 39.02%.

In the past few years, infectious diseases like COVID-19 have caused serious distress to the global society and the economy. To prevent its spread, the early detection and assessment of infectious diseases based on molecular tests or antigen testing of bodily have led to countless labor and material costs. Fortunately, with the rapid development of mobile localization and web techniques, the collected massive mobile trajectory data provide a promising solution for detecting positive cases. However, existing mobility data-driven infection case detection methods are limited in terms of modeling the complicated epidemic spreading processes and preserving user privacy of the mobility data. In this article, we propose a novel graph convolutional networks (GCN) model for detecting high-risk infection cases, where we incorporate a spatio-temporal hypergraph to model the complex interaction of individuals. Then, we elaborately design a privacy-preserving framework tightly coupled with the structure of the spatio-temporal hypergraph, which includes a mobility data obfuscation module to protect privacy and an accompanying confidence-aware mechanism to mitigate the consequent performance decline. Moreover, we introduce a causal propagation mechanism to further guarantee the temporal dependency and causal effect of the feature propagation in our spatio-temporal hypergraph, which introduces both the causal transform of node features and the causal gathering of edge features. Finally, extensive experiments on a large mobility dataset collected from location-based services (LBS) show that the proposed model improves the performance of infection case detection by at least 12.47% when compared with several widely adopted baselines. Besides, our code and datasets are available at the link ( https://github.com/wjfu99/EPI-HGNN ).

The binary relational knowledge base (KB, a.k.a. knowledge graph), representing real-world knowledge with binary relations and entities, has been an important research topic in artificial intelligence, while, considerable knowledge also involves beyond-binary relations. Recently, the area proposes to model n-ary relational KBs with both binary and beyond-binary relations included. However, most current models are extended from translational distance and neural network models in binary relational KBs, which suffer from weak expressiveness and high complexity, respectively. To overcome such issues, in this work, we propose a novel two-step modeling framework, GETD, generalizing the powerful tensor decomposition technique from binary relational KBs to the n-ary case. For n-ary relational KBs with single-arity relations, the GETD framework introduces Tucker decomposition and Tensor Ring decomposition for expressive and efficient modeling. Furthermore, the framework is technically extended for the representation of n-ary relational KBs with mixed-arity relations. The existing negative sampling technique is also generalized to the n-ary case for GETD. In addition, we theoretically prove that the GETD framework is fully expressive to completely represent any KBs. Empirical results on two representative datasets show that the proposed framework significantly outperforms the state-of-the-art methods, achieving 11–26% and 4–7% improvements on Hits@10 for the single-arity and the mixed-arity cases, respectively.

In order to prevent the re-emergence of an epidemic, predicting its trend while gaining insight into the intrinsic factors affecting it is a key issue in urban governance. Traditional SIR-like compartment models provide insight into the explanatory parameters of an outbreak, and the vast majority of existing deep learning models can predict the course of an outbreak well, but neither performs well in the other’s domain. Simultaneously, studying the commonalities and diversities in the causes of outbreaks among different countrywide regions is also a way to interrupt outbreaks. To address the issues of outbreak intrinsic relationships and prediction, we propose the Neural Compartmental Ordinary Differential Equations (NeuralCODE) model to study the relationship between population movements and outbreak development in different regions. Furthermore, to incorporate the commonalities and diversities in causes among different regions into the prediction and intrinsic inquiry problem, we propose an AutoML framework. Our results found that simply using the NeuralCODE algorithm could obtain better prediction and insight capabilities within different regions. With the introduction of AutoML, it became possible to explore the factors inherent in the epidemic’s development across regions and further improve the original algorithm’s predictive performance.

With the rapid advancement of communication technology and the exponential growth of mobile users, improving network coverage quality and throughput has become increasingly important. In particular, large-scale Base Station (BS) cooperative optimization has become a highly significant topic. BSs can adjust various parameters for high-quality communication, but automating this optimization remains challenging due to environmental sensitivity and interdependencies. Traditional methods for network optimization are constrained by the intricate nature of real-world environments. Further, Reinforcement Learning (RL) techniques, which are effective for configuration policies, encounter difficulties in intricate, high-dimensional wireless communication networks, especially in multi-agent cooperative optimization. To overcome these challenges, this article proposes the Enhanced Multi-Agent Proximal Policy Optimization (EMAPPO), which utilizes the capabilities of the UNet network to extract multi-spatial relationships among a massive number of network elements and employs the DiffPool network to efficiently depict the impact of large-scale action coordination among massive agents on coverage performance. To facilitate evaluation in communication optimization, we further introduce a high-fidelity digital twin-driven mobile network. Extensive experiments validate the effectiveness and superior performance of EMAPPO by utilizing the network digital twin. The results demonstrate significant improvements in signal coverage rate and network throughput compared to the competing methods.

Trajectory generation is a vital element in AI applications. Firstly, it enables simulation such as traffic simulation and epidemic spreading modeling. Secondly, it can provide synthetic privacy-preserving data for training AI models. Notably, trajectory generation featuring controllable user profiles holds substantial value in generating customized mobility trajectories tailored to diverse requirements. However, relevant work is still lacking. On the one hand, traditional deep generative models fall short in guiding controllable trajectory generation due to the statistical nature of human mobility patterns and the corresponding insufficient control mechanisms. On the other hand, though the diffusion model has demonstrated strong generative capabilities in many fields, to achieve controllable generation on discrete trajectory data, we still need to redesign the structure of the continuous diffusion model. In this article, we introduce a controllable trajectory generation framework that leverages a continuous diffusion model and classifier guidance for more robust condition control. Our proposed framework comprises two modules: a latent trajectory diffusion model and a trajectory classifier for profile guidance. Experiments on two real-world mobility datasets consistently demonstrate its capability of generating trajectories matching given user profiles and conforming to human mobility patterns. Our source code and trained models are released at https://github.com/tsinghua-fib-lab/User-Profile-Guided-Latent-Diffusion .

Synthesized human trajectories are crucial for a large number of applications. Existing solutions are mainly based on the generative adversarial network (GAN), which is limited due to the lack of modeling the human decision-making process. In this article, we propose a novel imitation learning-based method to synthesize human trajectories. This model utilizes a novel semantics-based interaction mechanism between the decision-making strategy and visitations to diverse geographical locations to model them in the semantic domain in a uniform manner. To augment the modeling ability to the real-world human decision-making policy, we propose a feature extraction model to extract the internal latent factors of variation of different individuals and then propose a novel self-attention-based policy net to capture the long-term correlation of mobility and decision-making patterns. Then, to better reward users’ mobility behavior, we propose a novel multi-scale reward net combined with mutual information to model the instant reward, long-term reward, and individual characteristics in a cohesive manner. Extensive experimental results on two real-world trajectory datasets show that our proposed model can synthesize the most high-quality trajectory data compared with six state-of-the-art baselines in terms of a number of key usability metrics and can well support practical applications based on trajectory data, demonstrating its effectiveness. Furthermore, our proposed method can learn explainable knowledge automatically from data, including explainable statistical features of trajectories and statistical relation between decision-making policy and features.

Recent technology development brings the boom of numerous new Demand-Driven Services (DDS) into urban lives, including ridesharing, on-demand delivery, express systems, and warehousing. In DDS, a service loop is an elemental structure, including its service worker, the service providers, and corresponding service targets. The service workers should transport either people or parcels from the providers to the target locations. Various planning tasks within DDS can thus be classified into two individual stages: (1) Dispatching, which is to form service loops from demand/supply distributions, and (2) Routing, which is to decide specific serving orders within the constructed loops. Generating high-quality strategies in both stages is important to develop DDS but faces several challenges. Meanwhile, deep reinforcement learning (DRL) has been developed rapidly in recent years. It is a powerful tool to solve these problems since DRL can learn a parametric model without relying on too many problem-based assumptions and optimize long-term effects by learning sequential decisions. In this survey, we first define DDS, then highlight common applications and important decision/control problems within. For each problem, we comprehensively introduce the existing DRL solutions. We also introduce open simulation environments for development and evaluation of DDS applications. Finally, we analyze remaining challenges and discuss further research opportunities in DRL solutions for DDS.

Urban spatio-temporal prediction is crucial for informed decision-making, such as traffic management, resource optimization, and emergency response. Despite remarkable breakthroughs in pretrained natural language models that enable one model to handle diverse tasks, a universal solution for spatio-temporal prediction remains challenging. Existing prediction approaches are typically tailored for specific spatio-temporal scenarios, requiring task-specific model designs and extensive domain-specific training data. In this study, we introduce UniST, a universal model designed for general urban spatio-temporal prediction across a wide range of scenarios. Inspired by large language models, UniST achieves success through: (i) utilizing diverse spatio-temporal data from different scenarios, (ii) effective pre-training to capture complex spatio-temporal dynamics, (iii) knowledge-guided prompts to enhance generalization capabilities. These designs together unlock the potential of building a universal model for various scenarios. Extensive experiments on more than 20 spatio-temporal scenarios, including grid-based data and graph-based data, demonstrate UniST’s efficacy in advancing state-of-the-art performance, especially in few-shot and zero-shot prediction.

Generating mobile traffic in urban environments is important for network planning and optimization. However, existing models show weakness in capturing spatial-temporal dynamics between mobile traffic and urban environments. This makes it difficult for the models to generate high-fidelity traffic data and control the generation process across different regions in large-scale urban environments, ultimately affecting the effectiveness of optimization strategies. In this paper, we propose a Spatio-Temporal Knowledge-driven Diffusion model (STK-Diff) for controllable mobile traffic generation. We construct an Urban Knowledge Graph (UKG) to fully characterize the urban features, which incorporates both the spatial and semantic relations of different entities, such as base stations, business areas, and functional regions. Based on the constructed UKG, we design the denoising network of diffusion model with a temporal extraction module and a spatial connection module. These two modules capture the correlations of mobile traffic and environment features via a frequency attention mechanism and spatial graph learning scheme, so as to make a strong controllability on the generated mobile traffic. Extensive experiments on three real-world datasets show that the proposed framework not only improves generation fidelity by up to 19%, but also enhances the controllability to generate specific patterns, with a gain of surpassing 15%.

App usage prediction aims to predict the next app most likely to be used based on historical behaviors, which is beneficial for smartphone system optimization, such as system resource management, battery energy optimization, and user experience enhancement. Existing studies have treated it as a simple time series prediction problem and overlooked the sessionization characteristic of mobile app usage, i.e., neglecting the intent context in which the user interacts with apps. In this paper, we explore the context of user intents and incorporate app sessionization features into prediction models to improve prediction accuracy. Specifically, we first extract the semantic meaning of spatio-temporal contextual information of app usage by constructing an urban knowledge graph. Second, we devise a hypergraph-based embedding model to extract the hyper-relations of intra-session apps. Third, we utilize a self-attention mechanism to fuse intra-session apps’ representations and combine spatio-temporal contextual embedding to form the session representation. We further leverage a transformer for inter-session intent transition modeling to extract users’ dynamic intent (i.e., the semantic meaning of sessions) for app usage. Finally, we jointly fuse dynamic intent and recently used app features using the MLP model for the prediction. The novelty of our method is that we are the first to leverage dynamic hypergraphs for modeling sessionization features, and we model both inter-session and intra-session relations. We evaluate our model based on two real-world datasets collected in Shanghai and Nanchang. In terms of prediction accuracy, mean reciprocal rank, and normalized discounted cumulative gain, our proposed framework outperforms state-of-the-art baselines by more than 30% in the Shanghai dataset and 20% in the Nanchang dataset, respectively.

Large language models (LLMs) have recently garnered significant attention in various domains, including recommendation systems. Recent research leverages the capabilities of LLMs to improve the performance and user modeling aspects of recommender systems. These studies primarily focus on utilizing LLMs to interpret textual data in recommendation tasks. However, it's worth noting that in ID-based recommendations, textual data is absent, and only ID data is available. The untapped potential of LLMs for ID data within the ID-based recommendation paradigm remains relatively unexplored. To this end, we introduce a pioneering approach called “LLM for ID-based recommendation” (LLM4IDRec). This innovative approach integrates the capabilities of LLMs while exclusively relying on ID data, thus diverging from the previous reliance on textual data. The basic idea of LLM4IDRec is that by employing LLM to augment ID data, if augmented ID data can improve recommendation performance, it demonstrates the ability of LLM to interpret ID data effectively, exploring an innovative way for the integration of LLM in ID-based recommendation. Specifically, we first define a prompt template to enhance LLM's ability to comprehend ID data and the ID-based recommendation task. Next, during the process of generating training data using this prompt template, we develop two efficient methods to capture both the local and global structure of ID data. We feed this generated training data into the LLM and employ LoRA for fine-tuning LLM. Following the fine-tuning phase, we utilize the fine-tuned LLM to generate ID data that aligns with users’ preferences. We design two filtering strategies to eliminate invalid generated data. Thirdly, we can merge the original ID data with the generated ID data, creating augmented data. Finally, we input this augmented data into the existing ID-based recommendation models without any modifications to the recommendation model itself. We evaluate the effectiveness of our LLM4IDRec approach using three widely used datasets. Our results demonstrate a notable improvement in recommendation performance, with our approach consistently outperforming existing methods in ID-based recommendation by solely augmenting input data.

Collaborative recommendation fundamentally involves learning high-quality user and item representations from interaction data. Recently, graph convolution networks (GCNs) have advanced the field by utilizing high-order connectivity patterns in interaction graphs, as evidenced by state-of-the-art methods like PinSage and LightGCN. However, one key limitation has not been well addressed in existing solutions: capturing long-range collaborative filtering signals, which are crucial for modeling user preference. In this work, we propose a new graph transformer (GT) framework— Position-aware Graph Transformer for Recommendation (PGTR), which combines the global modeling capability of Transformer blocks with the local neighborhood feature extraction of GCNs. The key insight is to explicitly incorporate node position and structure information from the user-item interaction graph into GT architecture via several purpose-designed positional encodings. The long-range collaborative signals from the Transformer block are then combined linearly with the local neighborhood features from the GCN backbone to enhance node embeddings for final recommendations. Empirical studies demonstrate the effectiveness of the proposed PGTR method when implemented on various GCN-based backbones across four real-world datasets and the robustness against interaction sparsity as well as noise. Our implementations are available in GitHub: https://github.com/MEICRS/PGTR .

Dynamic graph learning on temporal networks aims to understand the continuous evolution pattern of networks, with an important application on forecasting the future temporal network. Existing methods mainly focus on modeling the structural and temporal features, with recent research interest shifting toward considering the structural correlations between nodes through their neighbor co-occurrences. Though satisfactory performance has been achieved, there still remain several limitations: (1) the deviation of investigated scenarios from real-world applications, since most previous researches concentrate on special cases of multigraphs with abundant repeat edges; (2) the insufficient computational efficiency of modeling the structural features, since the existing neighbor co-occurrence scheme fails to consider explicit structural correlations between nodes and suffers from a time-consuming pairwise encoding strategy; (3) the unsatisfying prediction accuracy due to inadequate modeling of temporal features, since each neighbor’s historical temporal features and the temporal domain shifting with network evolving are both neglected. To solve these issues, we first focus on the general scenarios of temporal networks without abundant repeat edges for approaching the actual applications and propose an efficient and effective dynamic graph learning method named LightDyG. Specifically, (1) on the one hand, to increase the computational efficiency, LightDyG decouples the structural correlations between nodes and their individual substructures for fast convergence based on the analysis of existing co-occurrence mechanism, and further designs an incremental strategy for efficient structural encoding; (2) on the other hand, to improve the prediction accuracy, the temporal characteristics are considered by including both the interaction and appearance timestamps of neighbors, and a time-invariant temporal encoding strategy is designed to eliminate the temporal bias introduced by the network evolution. Extensive experiments conducted on four public temporal networks demonstrate that LightDyG outperforms the best baselines by 4.54–11.39% and 6.06–16.24% in terms of AP and AUC on the temporal link prediction tasks, respectively. In addition, LightDyG reduces the time cost for training and test up to 45.91% and 63.94%, respectively, and also achieves a fast convergence speed during training. The implementation of our approach is available in https://github.com/nudtzpan/LightDyG .

The mainstream approach of GNN-based recommendation aggregates high-order ID information associated with the node in the user-item graph. The aggregation pattern using ID as signal has two disadvantages: lack of textual semantics and the impact of interaction noise. These disadvantages pose a threat to effectively learn user preferences, especially in capturing intricate user-item semantic relationships. Although large language models (LLMs) allow the integration of rich textual information into recommenders and have had groundbreaking applications in recommender systems, current works need to bridge the gap between different representation spaces. This is because LLM-based methods align the representations of GNN-based models only by using text embedding of LLM, leading to unsatisfactory results. To address this challenge, we propose a denoising alignment framework with LLMs for GNN-based recommenders (DALR) , which aims to align structural representation with textual representation and mitigate the effects of noise. Specifically, we propose a modeling framework that integrates the representation of graph structure with textual information from LLMs to capture intricate user-item interactions. We also suggest an alignment paradigm to enhance representation performance by aligning semantic signals from LLMs and structural features from GNN models. Additionally, we introduce a contrastive learning scheme to relieve the impact of noise and improve model performance. Extensive experiments on public datasets demonstrate that our model consistently outperforms the state-of-the-art methods. DALR achieves improvements ranging from 2.82% to 12.20% in Recall@5 and from 1.04% to 3.48% in NDCG@5 compared to the strongest baseline model, using the Steam dataset as an example.

Session-based recommendation (SBR) methods often rely on user behavior data, which can struggle with the sparsity of session data, limiting performance. Researchers have identified that beyond behavioral signals, rich semantic information in item descriptions is crucial for capturing hidden user intent. While Large Language Models (LLMs) offer new ways to leverage this semantic data, the challenges of session anonymity, short-sequence nature, and high LLM training costs have hindered the development of a lightweight, efficient LLM framework for SBR. To address the above challenges, we propose an LLM-enhanced SBR framework that integrates semantic and behavioral signals from multiple views. This two-stage framework leverages the strengths of both LLMs and traditional SBR models while minimizing training costs. In the first stage, we use multi-view prompts to infer latent user intentions at the session semantic level, supported by an intent localization module to alleviate LLM hallucinations. In the second stage, we align and unify these semantic inferences with behavioral representations, effectively merging insights from both large and small models. Extensive experiments on two real datasets demonstrate that the LLM4SBR framework can effectively improve model performance. We release our codes along with the baselines at https://github.com/tsinghua-fib-lab/LLM4SBR .

Recovering fine-grained urban vehicle trajectory data hold great potential for understanding mobility patterns and improving the efficiency of transportation systems. Most existing solutions rely on regularly sampled GPS points, which capture data only from participating vehicles. In this work, we exploit traffic camera observation data for city-wide vehicle trajectory recovery. Nevertheless, there are two major challenges. First, traffic cameras are sparsely deployed at road intersections, resulting in uneven vehicle observations and irregular sampling intervals. Second, substantial uncertainty arises when reconstructing trajectories between distant consecutive observations. To address the above challenges, we propose TR-ODE , a novel encoder-decoder framework based on Neural Ordinary Differential Equations for continuous-time trajectory recovery. Specifically, TR-ODE employs customized GRU-ODE-Bayes to evolve hidden states between observations and update the current hidden state to incorporate the incoming observations. By incorporating a multi-task learning block, TrajRec , our method integrates road embeddings and self-attention scores to assist in simultaneous predictions on road segments and moving ratios for trajectory recovery. Extensive experimental studies on two real-world datasets demonstrate that TR-ODE outperforms state-of-the-art methods in vehicle trajectory recovery from irregular observations, reducing MAE and RMSE by up to 17.11% and 14.47%, respectively.

Modeling information diffusion on social networks can be used to guide the prediction and control of information propagation and improve the structure and functionality of social networks. Existing information diffusion prediction methods can predict information diffusion paths and its volume by modeling social network structure and user behavior. However, none of the existing methods take user activity level, which is proved to be critical in modeling the information diffusion process, into account, thus weaken the prediction accuracy. To solve this problem, this article proposes a Multi-Scale Activity Network (MSA-Net) to capture topological and historical affect features for different scales and to predict the users who will be affected at a specific future timestamp with the help of user activity level. Specifically, we first learn the network representation of three scales or levels: micro-scale, meso-scale, and macro-scale, which refers to the user level, intra-community level, and inter-community level, respectively. Then, we introduce the user activity level for each user by using user degree and average number of tweets per time unit to model the individual differences of users to achieve a more accurate prediction. Extensive experiments based on real-world datasets show that MSA-Net achieves a 6.14% improvement in terms of precision, a 6.74% improvement in terms of recall metrics, a 4.26% improvement in terms of F1-score, a 3.15% improvement in terms of MAP, and a 25.78% improvement in terms of NRMSE over the best existing baseline. The code and data are available at https://github.com/tsinghua-fib-lab/MSA-Net.

Crowd simulation holds crucial applications in various domains, such as urban planning, architectural design, and traffic arrangement. In recent years, physics-informed machine learning methods have achieved state-of-the-art performance in crowd simulation but fail to model the heterogeneity and multi-modality of human movement comprehensively. In this paper, we propose a social physics-informed diffusion model named SPDiff to mitigate the above gap. SPDiff takes both the interactive and historical information of crowds in the current timeframe to reverse the diffusion process, thereby generating the distribution of pedestrian movement in the subsequent timeframe. Inspired by the well-known social physics model, i.e., Social Force, regarding crowd dynamics, we design a crowd interaction encoder to guide the denoising process and further enhance this module with the equivariant properties of crowd interactions. To mitigate error accumulation in long-term simulations, we propose a multi-frame rollout training algorithm for diffusion modeling. Experiments conducted on two real-world datasets demonstrate the superior performance of SPDiff in terms of both macroscopic and microscopic evaluation metrics. Code and appendix are available at https://github.com/tsinghua-fib-lab/SPDiff.

Accounting for over 20% of the total carbon emissions, the precise estimation of on-road transportation carbon emissions is crucial for carbon emission monitoring and efficient mitigation policy formulation. However, existing estimation methods typically depend on hard-to-collect individual statistics of vehicle miles traveled to calculate emissions, thereby suffering from high data collection difficulty. To relieve this issue by utilizing the strong pattern recognition of artificial intelligence, we incorporate two sources of open data representative of the transportation demand and capacity factors, the origin-destination (OD) flow data and the road network data, to build a hierarchical heterogeneous graph learning method for on-road carbon emission estimation (HENCE). Specifically, a hierarchical graph consisting of the road network level, community level, and region level is constructed to model the multi-scale road network-based connectivity and travel connection between spatial areas. Heterogeneous graphs consisting of OD links and spatial links are further built at both the community level and region level to capture the intrinsic interactions between travel demand and road network accessibility. Extensive experiments on two large-scale real-world datasets demonstrate HENCE's effectiveness and superiority with R-squared exceeding 0.75 and outperforming baselines by 9.60% on average, validating its success in pioneering the use of artificial intelligence to empower carbon emission management and sustainability development. The implementation codes are available at this link: https://github.com/tsinghua-fib-lab/HENCE.

Urban villages, defined as informal residential areas in or around urban centers, are characterized by inadequate infrastructures and poor living conditions, closely related to the Sustainable Development Goals (SDGs) on poverty, adequate housing, and sustainable cities. Traditionally, governments heavily depend on field survey methods to monitor the urban villages, which however are time-consuming, labor-intensive, and possibly delayed. Thanks to widely available and timely updated satellite images, recent studies develop computer vision techniques to detect urban villages efficiently. However, existing studies either focus on simple urban village image classification or fail to provide accurate boundary information. To accurately identify urban village boundaries from satellite images, we harness the power of the vision foundation model and adapt the Segment Anything Model (SAM) to urban village segmentation, named UV-SAM. Specifically, UV-SAM first leverages a small-sized semantic segmentation model to produce mixed prompts for urban villages, including mask, bounding box, and image representations, which are then fed into SAM for fine-grained boundary identification. Extensive experimental results on two datasets in China demonstrate that UV-SAM outperforms existing baselines, and identification results over multiple years show that both the number and area of urban villages are decreasing over time, providing deeper insights into the development trends of urban villages and sheds light on the vision foundation models for sustainable cities. The dataset and codes of this study are available at https://github.com/tsinghua-fib-lab/UV-SAM.

The advent of artificial intelligence has led to a growing emphasis on data-driven modeling in macroeconomics, with agent-based modeling (ABM) emerging as a prominent bottom-up simulation paradigm.In ABM, agents (e.g., households, firms) interact within a macroeconomic environment, collectively generating market dynamics.Existing agent modeling typically employs predetermined rules or learningbased neural networks for decision-making.However, customizing each agent presents significant challenges, complicating the modeling of agent heterogeneity.Additionally, the influence of multi-period market dynamics and multifaceted macroeconomic factors are often overlooked in decision-making processes.In this work, we introduce EconAgent, a large language model-empowered agent with humanlike characteristics for macroeconomic simulation.We first construct a simulation environment that incorporates various market dynamics driven by agents' decisions regarding work and consumption.Through the perception module, we create heterogeneous agents with distinct decision-making mechanisms.Furthermore, we model the impact of macroeconomic trends using a memory module, which allows agents to reflect on past individual experiences and market dynamics.Simulation experiments show that EconAgent can make realistic decisions, leading to more reasonable macroeconomic phenomena compared to existing rule-based or learning-based agents.

The substantial social and financial costs of infrastructure identification impede in-depth analyses of sustainable urban design, especially in developing countries. In this paper, we present a novel framework with interactive web visualization based on geospatial visual foundation models. Leveraging this framework, we examine the urban infrastructure information in 1,178 cities worldwide, covering 93, 088 km2 areas. Cross-validation reveals that the overall accuracy of identified infrastructure achieves 67.0%. It sheds light on the sustainable development of cities and exposes the stark inequity in urban infrastructure provision for vulnerable populations. The identified urban infrastructure dataset of this study are available at https://github.com/tsinghua-fib-lab/GUI, and the interactive web application is at https://tinyurl.com/yz7xbfy3.

Identifying urban land-use types is crucial for effective resource management, urban planning, and sustainable development. However, classifying land use is complex due to the complexity of the city and the poor data available in undeveloped areas. In this work, we present the Multi-modal Model for Land-use Classification (M3LUC). Our model is the first to leverage the advanced Vision-Language Model (VLM) to better capture urban functionality through remote sensing data and Points of Interest (POI). We have also designed specific mechanisms to robustly and extensively tackle the modality missing and conflict to enhance transferability. Experiments conducted in four major cities in China demonstrate our model's superior performance in both transfer and non-transfer tasks, revealing its potential for broader applications.

The fifth-generation (5G) mobile network has significantly enhanced people's lives with faster internet speed and more reliable connections. However, there is still insufficient coverage of 5G networks worldwide, requiring telecom operators to deploy more base stations to meet the increasing demand for 5G's further commercialization. In this regard, a major challenge is understanding user network behaviors and traffic demands in target areas where 5G has not yet been deployed, which is crucial for developing a more efficient base station deployment strategy. Mobile traffic generation is a potential approach that enables operators to preemptively estimate user network demands in target areas, thereby specifying corresponding deployment strategies to enhance network performance. However, existing methods have limitations in capturing spatio-temporal features of 5G mobile traffic, particularly in areas with insufficient 5G coverage and limited historical 5G traffic data. To fill this gap, we introduce a regional feature conditioned diffusion framework for 5G network traffic generation. Our models explore the relationship between 5G traffic and existing 4G traffic, utilizing a customized cross attention mechanism and graph convolutional networks (GCN) to capture the correlation between network traffic and regional features. Based on this relationship, the framework can characterize mobile network traffic demands, thereby achieving high-fidelity 5G traffic generation in target regions with insufficient 5G coverage. Extensive experiments on real-world datasets have shown that the proposed scheme outperforms state-of-the-art baselines by more than 10%, demonstrating its high-fidelity generation capability, controllability, and generalizability. Moreover, we have deployed our scheme on China Mobile's Jiutian Platform as a network traffic simulator to improve 5G base station deployment strategies.

The facility location problem (FLP) is a classical combinatorial optimization challenge aimed at strategically laying out facilities to maximize their accessibility. In this paper, we propose a reinforcement learning method tailored to solve large-scale urban FLP, capable of producing near-optimal solutions at superfast inference speed. We distill the essential swap operation from local search, and simulate it by intelligently selecting edges on a graph of urban regions, guided by a knowledge-informed graph neural network, thus sidestepping the need for heavy computation of local search. Extensive experiments on four US cities with different geospatial conditions demonstrate that our approach can achieve comparable performance to commercial solvers with less than 5% accessibility loss, while displaying up to 1000 times speedup. We deploy our model as an online geospatial application at https://huggingface.co/spaces/tsinghua-fib-lab/MFLP.

Accurately estimating package delivery time is essential to the logistics industry, which enables reasonable work allocation and on-time service guarantee. This becomes even more necessary in mixed logistics scenarios where couriers handle a high volume of delivery and a smaller number of pickup simultaneously. However, most of the related works treat the pickup and delivery patterns on couriers' decision behavior equally, neglecting that the pickup has a greater impact on couriers' decision-making compared to the delivery due to its tighter time constraints. In such context, we have three main challenges: 1) multiple spatiotemporal factors are intricately interconnected, significantly affecting couriers' delivery behavior; 2) pickups have stricter time requirements but are limited in number, making it challenging to model their effects on couriers' delivery process; 3) couriers' spatial mobility patterns are critical determinants of their delivery behavior, but have been insufficiently explored. To deal with these, we propose TransPDT, a Transformer-based multi-task package delivery time prediction model. We first employ the Transformer encoder architecture to capture the spatio-temporal dependencies of couriers' historical travel routes and pending package sets. Then we design the pattern memory to learn the patterns of pickup in the imbalanced dataset via attention mechanism. We also set the route prediction as an auxiliary task of delivery time prediction, and incorporate the prior courier spatial movement regularities in prediction. Extensive experiments on real industry-scale datasets demonstrate the superiority of our method. A system based on TransPDT is deployed internally in JD Logistics to track more than 2000 couriers handling hundreds of thousands of packages per day in Beijing, and the average daily delivery timely rate of deployed stations is 0.68% higher than the non-deployed stations.

Spatio-temporal modeling is foundational for smart city applications, yet it is often hindered by data scarcity in many cities and regions. To bridge this gap, we propose a novel generative pre-training framework, GPD, for spatio-temporal few-shot learning with urban knowledge transfer. Unlike conventional approaches that heavily rely on common feature extraction or intricate few-shot learning designs, our solution takes a novel approach by performing generative pre-training on a collection of neural network parameters optimized with data from source cities. We recast spatio-temporal few-shot learning as pre-training a generative diffusion model, which generates tailored neural networks guided by prompts, allowing for adaptability to diverse data distributions and city-specific characteristics. GPD employs a Transformer-based denoising diffusion model, which is model-agnostic to integrate with powerful spatio-temporal neural networks. By addressing challenges arising from data gaps and the complexity of generalizing knowledge across cities, our framework consistently outperforms state-of-the-art baselines on multiple real-world datasets for tasks such as traffic speed prediction and crowd flow prediction. The implementation of our approach is available: https://github.com/tsinghua-fib-lab/GPD.

Rule learning is critical to improving knowledge graph (KG) reasoning due to their ability to provide logical and interpretable explanations. Recently, Graph Neural Networks (GNNs) with tail entity scoring achieve the state-of-the-art performance on KG reasoning. However, the theoretical understandings for these GNNs are either lacking or focusing on single-relational graphs, leaving what the kind of rules these GNNs can learn an open problem. We propose to fill the above gap in this paper. Specifically, GNNs with tail entity scoring are unified into a common framework. Then, we analyze their expressivity by formally describing the rule structures they can learn and theoretically demonstrating their superiority. These results further inspire us to propose a novel labeling strategy to learn more rules in KG reasoning. Experimental results are consistent with our theoretical findings and verify the effectiveness of our proposed method. The code is publicly available at https://github.com/LARS-research/Rule-learning-expressivity.

Stance detection automatically detects the stance in a text towards a target, vital for content analysis in web and social media research. Despite their promising capabilities, LLMs encounter challenges when directly applied to stance detection. First, stance detection demands multi-aspect knowledge, from deciphering event-related terminologies to understanding the expression styles in social media platforms. Second, stance detection requires advanced reasoning to infer authors' implicit viewpoints, as stances are often subtly embedded rather than overtly stated in the text. To address these challenges, we design a three-stage framework COLA (short for Collaborative rOle-infused LLM-based Agents) in which LLMs are designated distinct roles, creating a collaborative system where each role contributes uniquely. Initially, in the multidimensional text analysis stage, we configure the LLMs to act as a linguistic expert, a domain specialist, and a social media veteran to get a multifaceted analysis of texts, thus overcoming the first challenge. Next, in the reasoning-enhanced debating stage, for each potential stance, we designate a specific LLM-based agent to advocate for it, guiding the LLM to detect logical connections between text features and stance, tackling the second challenge. Finally, in the stance conclusion stage, a final decision maker agent consolidates prior insights to determine the stance. Our approach avoids extra annotated data and model training and is highly usable. We achieve state-of-the-art performance across multiple datasets. Ablation studies validate the effectiveness of each role design in handling stance detection. Further experiments have demonstrated the explainability and the versatility of our approach. Our approach excels in usability, accuracy, effectiveness, explainability and versatility, highlighting its value.

Heterogeneous information networks (HIN) have gained increasing popularity in recent years for capturing complex relations between diverse types of nodes. Meta-structures are proposed as a useful tool to identify the important patterns in HINs, but hand-crafted meta-structures pose significant challenges for scaling up, drawing wide research attention towards developing automatic search algorithms. Previous efforts primarily focused on searching for meta-structures with good empirical performance, overlooking the importance of human comprehensibility and generalizability. To address this challenge, we draw inspiration from the emergent reasoning abilities of large language models (LLMs). We propose ReStruct, a meta-structure search framework that integrates LLM reasoning into the evolutionary procedure. ReStruct uses a grammar translator to encode the meta-structures into natural language sentences, and leverages the reasoning power of LLMs to evaluate their semantic feasibility. Besides, ReStruct also employs performance-oriented evolutionary operations. These two competing forces allow ReStruct to jointly optimize the semantic explainability and empirical performance of meta-structures. Furthermore, ReStruct contains a differential LLM explainer to generate and refine natural language explanations for the discovered meta-structures by reasoning through the search history. Experiments on eight representative HIN datasets demonstrate that ReStruct achieves state-of-the-art performance in both recommendation and node classification tasks. Moreover, a survey study involving 73 graduate students shows that the discovered meta-structures and generated explanations by ReStruct are substantially more comprehensible. Our code and questionnaire are available at https://github.com/LinChen-65/ReStruct.

Urban spatio-temporal prediction is crucial for informed decision-making, such as traffic management, resource optimization, and emergence response. Despite remarkable breakthroughs in pretrained natural language models that enable one model to handle diverse tasks, a universal solution for spatio-temporal prediction remains challenging. Existing prediction approaches are typically tailored for specific spatio-temporal scenarios, requiring task-specific model designs and extensive domain-specific training data. In this study, we introduce UniST, a universal model designed for general urban spatio-temporal prediction across a wide range of scenarios. Inspired by large language models, UniST achieves success through: (i) utilizing diverse spatio-temporal data, (ii) effective pre-training to capture complex spatio-temporal relationships, (iii) spatio-temporal knowledge-guided prompts to enhance generalization capabilities. These designs together unlock the potential of building a universal model for various scenarios. Extensive experiments on more than 20 spatio-temporal scenarios demonstrate UniST's efficacy in advancing state-of-the-art performance, especially in few-shot and zero-shot prediction. The datasets and code implementation are released on https://github.com/tsinghua-fib-lab/UniST.

Mobile devices, especially smartphones, can support rich functions and have developed into indispensable tools in daily life. With the rise of generative AI services, smartphones can potentially transform into personalized assistants, anticipating user needs and scheduling services accordingly. Predicting user intents on smartphones, and reflecting anticipated activities based on past interactions and context, remains a pivotal step towards this vision. Existing research predominantly focuses on specific domains, neglecting the challenge of modeling diverse event sequences across dynamic contexts. Leveraging pre-trained language models (PLMs) offers a promising avenue, yet adapting PLMs to on-device user intent prediction presents significant challenges. To address these challenges, we propose PITuning, a Population-to-Individual Tuning framework. PITuning enhances common pattern extraction through dynamic event-to-intent transition modeling and addresses long-tailed preferences via adaptive unlearning strategies. Experimental results on real-world datasets demonstrate PITuning's superior intent prediction performance, highlighting its ability to capture long-tailed preferences and its practicality for on-device prediction scenarios.

Learning complex network dynamics is fundamental for understanding, modeling, and controlling real-world complex systems. Though great efforts have been made to predict the future states of nodes on networks, the capability of capturing long-term dynamics remains largely limited. This is because they overlook the fact that long-term dynamics in complex network are predominantly governed by their inherent low-dimensional manifolds, i.e., skeletons. Therefore, we propose the Dynamics-Invariant Skeleton Neural Net}work (DiskNet), which identifies skeletons of complex networks based on the renormalization group structure in hyperbolic space to preserve both topological and dynamics properties. Specifically, we first condense complex networks with various dynamics into simple skeletons through physics-informed hyperbolic embeddings. Further, we design graph neural ordinary differential equations to capture the condensed dynamics on the skeletons. Finally, we recover the skeleton networks and dynamics to the original ones using a degree-based super-resolution module. Extensive experiments across three representative dynamics as well as five real-world and two synthetic networks demonstrate the superior performances of the proposed DiskNet, which outperforms the state-of-the-art baselines by an average of 10.18\% in terms of long-term prediction accuracy. Code for reproduction is available at: https://github.com/tsinghua-fib-lab/DiskNet.

Predicting the resilience of complex networks, which represents the ability to retain fundamental functionality amidst external perturbations or internal failures, plays a critical role in understanding and improving real-world complex systems. Traditional theoretical approaches grounded in nonlinear dynamical systems rely on prior knowledge of network dynamics. On the other hand, data-driven approaches frequently encounter the challenge of insufficient labeled data, a predicament commonly observed in real-world scenarios. In this paper, we introduce a novel resilience prediction framework for complex networks, designed to tackle this issue through generative data augmentation of network topology and dynamics. The core idea is the strategic utilization of the inherent joint distribution present in unlabeled network data, facilitating the learning process of the resilience predictor by illuminating the relationship between network topology and dynamics. Experiment results on three network datasets demonstrate that our proposed framework TDNetGen can achieve high prediction accuracy up to 85%-95%. Furthermore, the framework still demonstrates a pronounced augmentation capability in extreme low-data regimes, thereby underscoring its utility and robustness in enhancing the prediction of network resilience. We have open-sourced our code in the following link, https://github.com/tsinghua-fib-lab/TDNetGen.

In large-scale metropolis, it is critical to efficiently allocate various resources such as electricity, medical care, and transportation to meet the living demands of citizens, according to the spatio-temporal distributions of resources and demands. Previous researchers have done plentiful work on such problems by leveraging Multi-Agent Reinforcement Learning (MARL) methods, where multiple agents cooperatively regulate and allocate the resources to meet the demands. However, facing the great number of agents in large cities, existing MARL methods lack efficient parameter sharing strategies among agents to reduce computational complexity. There remain two primary challenges in efficient parameter sharing: (1) during the RL training process, the behavior of agents changes significantly, limiting the performance of group parameter sharing based on fixed role division decided before training; (2) the behavior of agents forms complicated action trajectories, where their role characteristics are implicit, adding difficulty to dynamically adjusting agent role divisions during the training process. In this paper, we propose Dynamic Parameter Sharing (DyPS) to solve the above challenges. We design self-supervised learning tasks to extract the implicit behavioral characteristics from the action trajectories of agents. Based on the obtained behavioral characteristics, we propose a hierarchical MARL framework capable of dynamically revising the agent role divisions during the training process and thus shares parameters among agents with the same role, reducing computational complexity. In addition, our framework can be combined with various typical MARL algorithms, including IPPO, MAPPO, etc. We conduct 7 experiments in 4 representative resource allocation scenarios, where extensive results demonstrate our method's superior performance, outperforming the state-of-the-art baseline methods by up to 31%. Our source codes are available at https://github.com/tsinghua-fib-lab/DyPS.

Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not. Existing MIAs designed for large language models (LLMs) can be bifurcated into two types: reference-free and reference-based attacks. Although reference-based attacks appear promising performance by calibrating the probability measured on the target model with reference models, this illusion of privacy risk heavily depends on a reference dataset that closely resembles the training set. Both two types of attacks are predicated on the hypothesis that training records consistently maintain a higher probability of being sampled. However, this hypothesis heavily relies on the overfitting of target models, which will be mitigated by multiple regularization methods and the generalization of LLMs. Thus, these reasons lead to high false-positive rates of MIAs in practical scenarios. We propose a Membership Inference Attack based on Self-calibrated Probabilistic Variation (SPV-MIA). Specifically, we introduce a self-prompt approach, which constructs the dataset to fine-tune the reference model by prompting the target LLM itself. In this manner, the adversary can collect a dataset with a similar distribution from public APIs. Furthermore, we introduce probabilistic variation, a more reliable membership signal based on LLM memorization rather than overfitting, from which we rediscover the neighbour attack with theoretical grounding. Comprehensive evaluation conducted on three datasets and four exemplary LLMs shows that SPV-MIA raises the AUC of MIAs from 0.7 to a significantly high level of 0.9. Our code and dataset are available at: https://github.com/tsinghua-fib-lab/NeurIPS2024_SPV-MIA

Citation networks are critical infrastructures of modern science, serving as intricate webs of past literature and enabling researchers to navigate the knowledge production system. To mine information hiding in the link space of such networks, predicting which previous papers (candidates) will a new paper (query) cite is a critical problem that has long been studied. However, an important gap remains unaddressed: the roles of a paper's citations vary significantly, ranging from foundational knowledge basis to superficial contexts. Distinguishing these roles requires a deeper understanding of the logical relationships among papers, beyond simple edges in citation networks. The emergence of large language models (LLMs) with textual reasoning capabilities offers new possibilities for discerning these relationships, but there are two major challenges. First, in practice, a new paper may select its citations from gigantic existing papers, where the combined texts far exceed the context length of LLMs. Second, logical relationships between papers are often implicit, and directly prompting an LLM to predict citations may lead to results based primarily on surface-level textual similarities, rather than the deeper logical reasoning required. In this paper, we introduce the novel concept of core citation, which identifies the critical references that go beyond superficial mentions. Thereby, we elevate the citation prediction task from a simple binary classification to a more nuanced problem: distinguishing core citations from both superficial citations and non-citations. To address this, we propose $\textbf{HLM-Cite}$, a $\textbf{H}$ybrid $\textbf{L}$anguage $\textbf{M}$odel workflow for citation prediction, which combines embedding and generative LMs. We design a curriculum finetune procedure to adapt a pretrained text embedding model to coarsely retrieve high-likelihood core citations from vast candidate sets and then design an LLM agentic workflow to rank the retrieved papers through one-shot reasoning, revealing the implicit relationships among papers. With the two-stage pipeline, we can scale the candidate sets to 100K papers, vastly exceeding the size handled by existing methods. We evaluate HLM-Cite on a dataset across 19 scientific fields, demonstrating a 17.6\% performance improvement comparing SOTA methods. Our code is open-source at https://github.com/tsinghua-fib-lab/H-LM for reproducibility.

Urban planning, which aims to design feasible land-use configurations for target areas, has become increasingly essential due to the high-speed urbanization process in the modern era. However, the traditional urban planning conducted by human designers can be a complex and onerous task. Thanks to the advancement of deep learning algorithms, researchers have started to develop automated planning techniques. While these models have exhibited promising results, they still grapple with a couple of unresolved limitations: 1) Ignoring the relationship between urban functional zones and configurations and failing to capture the relationship among different functional zones. 2) Less interpretable and stable generation process. To overcome these limitations, we propose a novel generative framework based on normalizing flows, namely Dual-stage Urban Flows (DSUF) framework. Specifically, the first stage is to utilize zone-level urban planning flows to generate urban functional zones based on given surrounding contexts and human guidance. Then we employ an Information Fusion Module to capture the relationship among functional zones and fuse the information of different aspects. The second stage is to use configuration-level urban planning flows to obtain land-use configurations derived from fused information. We design several experiments to indicate that our framework can outperform for the urban planning task**.

Recommender systems filter out information that meets user interests. However, users may be tired of the recommendations that are too similar to the content they have been exposed to in a short historical period, which is the so-called user fatigue. Despite the significance for a better user experience, user fatigue is seldom explored by existing recommenders. In fact, there are three main challenges to be addressed for modeling user fatigue, including what features support it, how it influences user interests, and how its explicit signals are obtained. In this paper, we propose to model user Fatigue in interest learning for sequential Recommendations (FRec). To address the first challenge, based on a multi-interest framework, we connect the target item with historical items and construct an interest-aware similarity matrix as features to support fatigue modeling. Regarding the second challenge, built upon feature cross, we propose a fatigue-enhanced multi-interest fusion to capture long-term interest. In addition, we develop a fatigue-gated recurrent unit for short-term interest learning, with temporal fatigue representations as important inputs for constructing update and reset gates. For the last challenge, we propose a novel sequence augmentation to obtain explicit fatigue signals for contrastive learning. We conduct extensive experiments on real-world datasets, including two public datasets and one large-scale industrial dataset. Experimental results show that FRec can improve AUC and GAUC up to 0.026 and 0.019 compared with state-of-the-art models, respectively. Moreover, large-scale online experiments demonstrate the effectiveness of FRec for fatigue reduction. Our codes are released at https://github.com/tsinghua-fib-lab/SIGIR24-FRec.

In modern recommender systems, sequential recommendation leverages chronological user behaviors to make effective next-item suggestions, which suffers from data sparsity issues, especially for new users. One promising line of work is the cross-domain recommendation, which trains models with data across multiple domains to improve the performance in data-scarce domains. Recent proposed cross-domain sequential recommendation models such as PiNet and DASL have a common drawback relying heavily on overlapped users in different domains, which limits their usage in practical recommender systems. In this paper, we propose a M ixed A ttention N etwork (MAN) with local and global attention modules to extract the domain-specific and cross-domain information. Firstly, we propose a local/global encoding layer to capture the domain-specific/cross-domain sequential pattern. Then we propose a mixed attention layer with item similarity attention, sequence-fusion attention, and group-prototype attention to capture the local/global item similarity, fuse the local/global item sequence, and extract the user groups across different domains, respectively. Finally, we propose a local/global prediction layer to further evolve and combine the domain-specific and cross-domain interests. Experimental results on two real-world datasets (each with two domains) demonstrate the superiority of our proposed model. Further study also illustrates that our proposed method and components are model-agnostic and effective, respectively. The code and data are available at https://github.com/Guanyu-Lin/MAN.

Modern personalized recommendation services often rely on user feedback, either explicit or implicit, to improve the quality of services. Explicit feedback refers to behaviors like ratings, while implicit feedback refers to behaviors like user clicks. However, in the scenario of full-screen video viewing experiences like Tiktok and Reels, the click action is absent, resulting in unclear feedback from users, hence introducing noises in modeling training. Existing approaches on de-noising recommendation mainly focus on positive instances while ignoring the noise in a large amount of sampled negative feedback. In this paper, we propose a meta-learning method to annotate the unlabeled data from loss and gradient perspectives, which considers the noises in both positive and negative instances. Specifically, we first propose anInverse Dual Loss (IDL) to boost the true label learning and prevent the false label learning. Then we further propose anInverse Gradient (IG) method to explore the correct updating gradient and adjust the updating based on meta-learning. Finally, we conduct extensive experiments on both benchmark and industrial datasets where our proposed method can significantly improve AUC by 9.25% against state-of-the-art methods. Further analysis verifies the proposed inverse learning framework is model-agnostic and can improve a variety of recommendation backbones. The source code, along with the best hyper-parameter settings, is available at this link: https://github.com/Guanyu-Lin/InverseLearning.

Multimodal recommender systems have acquired applications in broad web scenarios such as e-commerce businesses and short-video platforms. Existing multimodal recommendation methods generally boost performance by introducing item-side multimodal content as supplement information. However, the common training paradigm, i.e., encoding unimodal content respectively and fusing them to fit user preference scores, makes the model biased towards items with prevailing modality content under non-uniform training data. This results in a serious item-side unfairness issue, i.e., some items with prevailing modality content are over-recommended while a large number of items don't receive adequate recommendation opportunities, leaving corresponding content providers at great disadvantage. Aiming to eliminate such modality bias and promote item-side fairness, we propose a fairness-aware modality debiasing framework based on counterfactual inference. In the training stage, we additionally introduce unimodal prediction branches to capture the modality bias. In the inference stage, we conduct a fairness-aware counterfactual inference to adaptively eliminate the modality bias. The proposed framework is model-agnostic and flexible to be implemented in various multimodal recommendation models. Extensive experiments on two datasets demonstrate that the proposed method can significantly enhance item-side fairness while providing competitive recommendation accuracy. Our proposed framework is expected to help mitigate the unfair treatment experienced by vulnerable content providers on multimedia web platforms. Codes are available in https://github.com/tsinghua-fib-lab-WWW2024-Modality-Debiasing.

Collaborative Filtering (CF) plays a crucial role in modern recommender systems, leveraging historical user-item interactions to provide personalized suggestions. However, CF-based methods often encounter biases due to imbalances in training data. This phenomenon makes CF-based methods tend to prioritize recommending popular items and performing unsatisfactorily on inactive users. Existing works address this issue by rebalancing training samples, reranking recommendation results, or making the modeling process robust to the bias. Despite their effectiveness, these approaches can compromise accuracy or be sensitive to weighting strategies, making them challenging to train. Therefore, exploring how to mitigate these biases remains in urgent demand. In this article, we deeply analyze the causes and effects of the biases and propose a framework to alleviate biases in recommendation from the perspective of representation distribution, namely Group-Alignment and Global-Uniformity Enhanced Representation Learning for Debiasing Recommendation (AURL). Specifically, we identify two significant problems in the representation distribution of users and items, namely group-discrepancy and global-collapse. These two problems directly lead to biases in the recommendation results. To this end, we propose two simple but effective regularizers in the representation space, respectively named group-alignment and global-uniformity. The goal of group-alignment is to bring the representation distribution of long-tail entities closer to that of popular entities, while global-uniformity aims to preserve the information of entities as much as possible by evenly distributing representations. Our method directly optimizes both the group-alignment and global-uniformity regularization terms to mitigate recommendation biases. Please note that AURL applies to arbitrary CF-based recommendation backbones. Extensive experiments on three real datasets and various recommendation backbones verify the superiority of our proposed framework. The results show that AURL not only outperforms existing debiasing models in mitigating biases but also improves recommendation performance to some extent.

Understanding and accurately predicting cellular traffic data is vital for communication operators and device users, as it facilitates efficient resource allocation and ensures superior service quality. However, large-scale cellular traffic data forecasting remains challenging due to intricate temporal variations and complex spatial relationships. This article proposes a Knowledge Graph Driven Decomposition Approach (KGDA) for precise cellular traffic prediction. The KGDA breaks down the impact of static environmental factors and dynamic autocorrelations of cellular traffic time series, enabling the capture of overall traffic changes and understanding of traffic dependence on past values. Specifically, we propose an urban knowledge graph to capture the static environmental context of base stations, mapping these entities into the same latent space while retaining static environmental knowledge. The cellular traffic is divided into a regular pattern and fluctuating residual components, with the KGDA comprising four modules: a Knowledge Graph Representation Learning model, a traffic regular pattern prediction module, a traffic residual dynamic prediction module, and an attentional fusion module. The first leverages graph neural networks to extract spatial contexts and predict regular patterns, the second utilizes the Bi-directional Long Short-Term Memory (Bi-LSTM) model to capture autocorrelations of traffic time series, and the final module integrates the patterns and residuals to produce the final prediction result. Comprehensive experiments demonstrate that our proposed model outperforms state-of-the-art models by more than 10% in forecasting cellular traffic.

Vessel trajectory prediction is the key to maritime applications such as traffic surveillance, collision avoidance, anomaly detection, and so on. Making predictions more precisely requires a better understanding of the moving trend for a particular vessel since the movement is affected by multiple factors like marine environment, vessel type, and vessel behavior. In this paper, we propose a model named VesNet, based on the attentional seq2seq framework, to predict vessel future movement sequence by observing the current trajectory. Firstly, we extract the route patterns from the raw AIS data during preprocessing. Then, we design a multi-task learning structure to learn how to implement route pattern classification and vessel trajectory prediction simultaneously. By comparing with representative baseline models, we find that our VesNet has the best performance in terms of long-term prediction precision. Additionally, VesNet can recognize the route pattern by capturing the implicit moving characteristics. The experimental results prove that the proposed multi-task learning assists the vessel trajectory prediction mission.

In logistics service, the delivery timely rate is a key experience indicator, which is highly essential to the competitive advantage of express companies. Prediction on it enables intervention on couriers with low predicted results in advance, thus ensuring employee productivity and customer satisfaction. Currently, few related works focus on couriers’ level delivery timely rate prediction, and there are complex spatial correlations between couriers and road districts in the express scenario, which makes traditional real-time prediction approaches hard to utilize. To deal with this, we propose a deep spatial-temporal neural network, RCCNet to model spatial-temporal correlations. Specifically, we adopt Node2vec, which can encode the road network-based graph directly to capture spatial correlations between road districts. Further, we calculate couriers’ historical time-series similarity to build a graph and employ graph convolutional networks to capture the correlation between couriers. We also leverage historical sequential information with long short-term memory networks. We conduct experiments with real-world express datasets. Compared with other competitive baseline methods widely used in industry, the experiment results demonstrate its superior performance over multiple baselines.

Recovering the fine-grained working process of couriers is becoming one of the essential problems for improving the express delivery systems because knowing the detailed process of how couriers accomplish their daily work facilitates the analyzing, understanding, and optimizing of the working procedure. Although coarse-grained courier trajectories and waybill delivery time data can be collected, this problem is still challenging due to noisy data with spatio-temporal biases, lacking ground truth of couriers’ fine-grained behaviors, and complex correlations between behaviors. Existing works typically focus on a single dimension of the process such as inferring the delivery time and can only yield results of low spatio-temporal resolution, which cannot address the problem well. To bridge the gap, we propose a digital-twin-based iterative calibration system (DTRec) for fine-grained courier working process recovery. We first propose a spatio-temporal bias correction algorithm, which systematically improves existing methods in correcting waybill addresses and trajectory stay points. Second, to model the complex correlations among behaviors and inherent physical constraints, we propose an agent-based model to build the digital twin of couriers. Third, to further improve recovery performance, we design a digital-twin-based iterative calibration framework, which leverages the inconsistency between the deduction results of the digital twin and the recovery results from real-world data to improve both the agent-based model and the recovery results. Experiments show that DTRec outperforms state-of-the-art baselines by 10.8% in terms of fine-grained accuracy on real-world datasets. The system is deployed in the industrial practices in JD Logistics with promising applications. The code is available at https://github.com/tsinghua-fib-lab/Courier-DTRec .

Generally speaking, we can easily specify many causal relationships in the prediction tasks of ubiquitous computing, such as human activity prediction, mobility prediction, and health prediction. However, most of the existing methods in these fields failed to take advantage of this prior causal knowledge. They typically make predictions only based on correlations in the data, which hinders the prediction performance in real-world scenarios, because a distribution shift between training data and testing data generally exists. To fill in this gap, we proposed a Generative Adversarial Network (GAN)-based Causal Information Learning prediction framework, which can effectively leverage causal information to improve the prediction performance of existing ubiquitous computing deep learning models. Specifically, faced with a unique challenge that the treatment variable, referring to the intervention that influences the target in a causal relationship, is generally continuous in ubiquitous computing, the framework employs a representation learning approach with a GAN-based deep learning model. By projecting all variables except the treatment into a latent space, it effectively minimizes confounding bias and leverages the learned latent representation for accurate predictions. In this way, it deals with the continuous treatment challenge, and in the meantime, it can be easily integrated with existing deep learning models to lift their prediction performance in practical scenarios with causal information. Extensive experiments on two large-scale real-world datasets demonstrate its superior performance over multiple state-of-the-art baselines. We also propose an analytical framework together with extensive experiments to empirically show that our framework achieves better performance gain under two conditions: when the distribution differences between the training data and the testing data are more significant and when the treatment effects are larger. Overall, this work suggests that learning causal information is a promising way to improve the prediction performance of ubiquitous computing tasks. We open both our dataset and code 1 and call for more research attention in this area.

Predicting citizens’ visiting behaviors to urban facilities is instrumental for city governors and planners to detect inequalities in urban opportunities and optimize the distribution of facilities and resources. Previous works predict facility visits simply using observed visit behavior, yet citizens’ intrinsic demands for facilities are not characterized explicitly, causing potential incorrect learned relations in the prediction results. In this article, to make up for this deficiency, we present a demand-driven urban facility visit prediction method that decomposes citizens’ visits to facilities into their unobservable demands and their capability to fulfill them. Demands are expressed as the function of regional demographic attributes by a neural network, and the fulfillment capability is determined by the urban region’s spatial accessibility to facilities. Extensive evaluations of datasets of three large cities confirm the efficiency and rationality of our model. Our method outperforms the best state-of-the-art model by 8.28% on average in facility visit prediction tasks. Further analyses demonstrate the reasonableness of recovered facility demands and their relationship with citizen demographics. For instance, senior citizens tend to have higher medical demands but lower shopping demands. Meanwhile, estimated capabilities and accessibilities provide deeper insights into the decaying accessibility with respect to spatial distance and facilities’ diverse functions in the urban environment. Our findings shed light on demand-driven urban data mining and demand-based urban facility planning.

Vehicle routing problem with time window (VRPTW) is of great importance for a wide spectrum of services and real-life applications, such as online take-out and car-hailing platforms. A promising method should generate high-qualified solutions within limited inference time, and there are three major challenges: (a) directly optimizing the goal with several practical constraints; (b) efficiently handling individual time-window limits; and (c) modeling the cooperation among the vehicle fleet. In this article, we present an end-to-end reinforcement learning framework to solve VRPTW. First, we propose an agent model that encodes constraints into features as the input and conducts harsh policy on the output when generating deterministic results. Second, we design a time penalty augmented reward to model the time-window limits during gradient propagation. Third, we design a task handler to enable the cooperation among different vehicles. We perform extensive experiments on two real-world datasets and one public benchmark dataset. Results demonstrate that our solution improves the performance by up to 11.7% compared to other RL baselines and could generate solutions for instances within seconds, while existing heuristic baselines take for minutes as well as maintain the quality of solutions. Moreover, our solution is thoroughly analyzed with meaningful implications due to the real-time response ability.

Mobile user traffic facilitates diverse applications, including network planning and optimization, whereas large-scale mobile user traffic is hardly available due to privacy concerns. One alternative solution is to generate mobile user traffic data for downstream applications. However, existing generation models cannot simulate the multi-scale temporal dynamics in mobile user traffic on individual and aggregate levels. In this work, we propose a multi-scale hierarchical generative adversarial network (MSH-GAN) containing multiple generators and a multi-class discriminator. Specifically, the mobile traffic usage behavior exhibits a mixture of multiple behavior patterns, which are called micro-scale behavior patterns and are modeled by different pattern generators in our model. Moreover, the traffic usage behavior of different users exhibits strong clustering characteristics, with the co-existence of users with similar and different traffic usage behaviors. Thus, we model each cluster of users as a class in the discriminator’s output, referred to as macro-scale user clusters. Then, the gap between micro-scale behavior patterns and macro-scale user clusters is bridged by introducing the switch mode generators, which describe the traffic usage behavior in switching between different patterns. All users share the pattern generators. In contrast, the switch mode generators are only shared by a specific cluster of users, which models the multi-scale hierarchical structure of the traffic usage behavior of massive users. Finally, we urge MSH-GAN to learn the multi-scale temporal dynamics via a combined loss function, including adversarial loss, clustering loss, aggregated loss, and regularity terms. Extensive experiment results demonstrate that MSH-GAN outperforms state-of-art baselines by at least 118.17% in critical data fidelity and usability metrics. Moreover, observations show that MSH-GAN can simulate traffic patterns and pattern switch behaviors.

Nowadays, the explosive growth of personalized web applications and the rapid development of artificial intelligence technology have flourished the recent research on mobile user profiling, i.e., inferring the user profile from mobile behavioral data. Particularly, existing studies mainly follow the data-driven paradigm to develop feature engineering and representation learning on such data, which however suffer from the robustness issue, i.e., generalizing poorly across datasets and profiles without considering semantic knowledge therein. In comparison, the rising knowledge-driven paradigm built upon the knowledge graph (KG) offers a potential solution to mitigate such weakness. Therefore, in this article, we propose a Knowledge Graph aided framework for Mobile User Profiling (KG-MUP). Specifically, to distil semantic knowledge among data, we firstly construct an urban knowledge graph (UrbanKG) with domain entities like users, regions, point of interests (POIs), and so on. identified, as well as semantic relations for home, workplace, spatiality, and so on. extracted. Moreover, we leverage tensor decomposition and graph neural network to obtain knowledgeable user representations from UrbanKG. In addition, we introduce several customized features to quantify individual mobility characteristics for mobile user profiling. Extensive experiments on three real-world mobility datasets demonstrate that KG-MUP achieves state-of-the-art performance on user profile inference tasks. Moreover, further results also reveal the importance of various semantic knowledge to user profile inference, which provides meaningful insights on user modeling with mobile behavioral data.

Origin-destination (OD) flow contains population mobility information between every two regions in the city, which is of great value in urban planning and transportation management. Nevertheless, the collection of OD flow data is extremely difficult due to the hindrance of privacy issues and collection costs. Significant efforts have been made to generate OD flow based on urban regional features, e.g., demographics, land use, and so on, since spatial heterogeneity of urban function is the primary cause that drives people to move from one place to another. On the other hand, people travel through various routes between OD, which will have effects on urban traffic, e.g., road travel speed and time. These effects of OD flows reveal the fine-grained spatiotemporal patterns of population mobility. Few works have explored the effectiveness of incorporating urban traffic information into OD generation. To bridge this gap, we propose to generate real-world daily temporal OD flows enhanced by urban traffic information in this paper. Our model consists of two modules: Urban2OD and OD2Traffic . In the Urban2OD module, we devise a spatiotemporal graph neural network to model the complex dependencies between daily temporal OD flows and regional features. In the OD2Traffic module, we introduce an attention-based neural network to predict urban traffic based on OD flow from the Urban2OD module. Then, by utilizing gradient backpropagation, these two modules are able to enhance each other to generate high-quality OD flow data. Extensive experiments conducted on real-world datasets demonstrate the superiority of our proposed model over the state of the art.

The fastest route search, which is to find a path with the shortest travel time when the user initiates a query, has become one of the most important services in many map applications. To enhance the user experience of travel, it is necessary to achieve accurate and real-time route search. However, traffic conditions are changing dynamically, and the frequent occurrence of traffic congestion may greatly increase travel time. Thus, it is challenging to achieve the above goal. To deal with it, we present a congestion-aware spatio-temporal graph convolutional network-based A* search algorithm for the task of fastest route search. We first identify a sequence of consecutive congested traffic conditions as a traffic congestion event. Then, we propose a spatio-temporal graph convolutional network that jointly models the congestion events and changing travel time to capture their complex spatio-temporal correlations, which can predict the future travel-time information of each road segment as the basis of route planning. Further, we design a path-aided neural network to achieve effective origin-destination (OD) shortest travel-time estimation by encoding the complex relationships between OD pairs and their corresponding fastest paths. Finally, the cost function in the A* algorithm is set by fusing the output results of the two components, which is used to guide the route search. Our experimental results on the two real-world datasets show the superior performance of the proposed method.

A considerable amount of mobility data has been accumulated due to the proliferation of location-based services. Nevertheless, compared with mobility data from transportation systems like the GPS module in taxis, this kind of data is commonly sparse in terms of individual trajectories in the sense that users do not access mobile services and contribute their data all the time. Consequently, the sparsity inevitably weakens the practical value of the data even if it has a high user penetration rate. To solve this problem, we propose a novel attentional neural network-based model, named AttnMove, to densify individual trajectories by recovering unobserved locations at a fine-grained spatial-temporal resolution. To tackle the challenges posed by sparsity, we design various intra- and inter- trajectory attention mechanisms to better model the mobility regularity of users and fully exploit the periodical pattern from long-term history. In addition, to guarantee the robustness of the generated trajectories to avoid harming downstream applications, we also exploit the Bayesian approximate neural network to estimate the uncertainty of each imputation. As a result, locations generated by the model with high uncertainty will be excluded. We evaluate our model on two real-world datasets, and extensive results demonstrate the performance gain compared with the state-of-the-art methods. In-depth analyses of each design of our model have been conducted to understand their contribution. We also show that, by providing high-quality mobility data, our model can benefit a variety of mobility-oriented downstream applications.

With the rapid development of location acquisition technologies, massive mobile trajectories have been collected and made available to us, which support a fantastic way of understanding and modeling individuals’ mobility. However, existing data-driven methods either fail to capture the long-range dependency or suffer from a high computational cost. To overcome these issues, we propose a knowledge-driven framework for mobility prediction, which leverages knowledge graphs (KG) to formulate the mobility prediction task into the KG completion problem through integrating the structured “knowledge” from the mobility data. However, most related mobility prediction works only focus on the structured information encoded in existing triples, which ignores the rich semantic information of relation paths composed of multiple relation triples. In this article, we apply a dedicated module to extract the supplementary semantic structure of paths in KG, which contributes to the interpretability and accuracy of our model. Specifically, the extracted rules are applied to capture the dependencies between relational facts. Moreover, by incorporating user information in the entity-relation space with the corresponding hyperplane, our method could capture diverse user mobility patterns and model the personal characteristics of users to improve the accuracy of mobility prediction. Extensive evaluations illustrate that our proposed model beats state-of-the-art mobility prediction algorithms, which verifies the superiority of utilizing logical rules and user hyperplanes. Our implementation code is available at https://github.com/tsinghua-fib-lab/RulekG-MobiPre.git

Accurately predicting individual-level infection state is of great value since its essential role in reducing the damage of the epidemic. However, there exists an inescapable risk of privacy leakage in the fine-grained user mobility trajectories required by individual-level infection prediction. In this article, we focus on developing a framework of privacy-preserving individual-level infection prediction based on federated learning (FL) and graph neural networks (GNN). We proposeFalcon, aFederated grAphLearning method for privacy-preserving individual-level infeCtion predictiON. It utilizes a novel hypergraph structure with spatio-temporal hyperedges to describe the complex interactions between individuals and locations in the contagion process. By organically combining the FL framework with hypergraph neural networks, the information propagation process of the graph machine learning is able to be divided into two stages distributed on the server and the clients, respectively, so as to effectively protect user privacy while transmitting high-level information. Furthermore, it elaborately designs a differential privacy perturbation mechanism as well as a plausible pseudo location generation approach to preserve user privacy in the graph structure. Besides, it introduces a cooperative coupling mechanism between the individual-level prediction model and an additional region-level model to mitigate the detrimental impacts caused by the injected obfuscation mechanisms. Extensive experimental results show that our methodology outperforms state-of-the-art algorithms and is able to protect user privacy against actual privacy attacks. Our code and datasets are available at the link: https://github.com/wjfu99/FL-epidemic .

Recommender systems have become crucial in information filtering nowadays. Existing recommender systems extract user preferences based on the correlation in data, such as behavioral correlation in collaborative filtering, feature-feature, or feature-behavior correlation in click-through rate prediction. However, unfortunately, the real world is driven by causality , not just correlation, and correlation does not imply causation. For instance, recommender systems might recommend a battery charger to a user after buying a phone, where the latter can serve as the cause of the former; such a causal relation cannot be reversed. Recently, to address this, researchers in recommender systems have begun utilizing causal inference to extract causality, thereby enhancing the recommender system. In this survey, we offer a comprehensive review of the literature on causal inference-based recommendation. Initially, we introduce the fundamental concepts of both recommender system and causal inference as the foundation for subsequent content. We then highlight the typical issues faced by non-causality recommender system. Following that, we thoroughly review the existing work on causal inference-based recommender systems, based on a taxonomy of three-aspect challenges that causal inference can address. Finally, we discuss the open problems in this critical research area and suggest important potential future works.

Knowledge graphs (KGs) can help enhance recommendations, especially for the data-sparsity scenarios with limited user-item interaction data. Due to the strong power of representation learning of graph neural networks (GNNs), recent works of KG-based recommendation deploy GNN models to learn from both knowledge graph and user-item bipartite interaction graph. However, these works have not well considered the hierarchical structure of knowledge graph, leading to sub-optimal results. Despite the benefit of hierarchical structure, leveraging it is challenging since the structure is always partly-observed. In this work, we first propose to reveal unknown hierarchical structures with a supervised signal detection method and then exploit the hierarchical structure with disentangling representation learning. We conduct experiments on two large-scale datasets, of which the results well verify the superiority and rationality of the proposed method. Further experiments of ablation study with respect to key model designs have demonstrated the effectiveness and rationality of our proposed model. The code is available at https://github.com/tsinghua-fib-lab/HIKE .

Micro-video platforms such as TikTok are extremely popular nowadays. One important feature is that users no longer select interested videos from a set; instead, they either watch the recommended video or skip to the next one. As a result, the time length of users’ watching behavior becomes the most important signal for identifying preferences. However, our empirical data analysis has shown a video-length effect that long videos can more easily receive a higher value of average view time, and thus adopting such view-time labels for measuring user preferences can easily induce a biased model that favors the longer videos. In this article, we propose a V ideo L ength D ebiasing Rec ommendation (VLDRec) method to alleviate such an effect for micro-video recommendation. VLDRec designs the data labeling approach and the sample generation module that better capture user preferences in a view-time-oriented manner. It further leverages the multi-task learning technique to jointly optimize the above samples with the original biased ones. Extensive experiments show that VLDRec can improve users’ view time by 1.81% and 11.32% on two real-world datasets, given a recommendation list of a fixed overall video length, compared with the best baseline method. Moreover, VLDRec is also more effective in matching users’ interests in terms of the video content.

Recently, the user-side fairness issue in Collaborative Filtering (CF) algorithms has gained considerable attention, arguing that results should not discriminate an individual or a sub-user group based on users’ sensitive attributes (e.g., gender). Researchers have proposed fairness-aware CF models by decreasing statistical associations between predictions and sensitive attributes. A more natural idea is to achieve model fairness from a causal perspective. The remaining challenge is that we have no access to interventions, i.e., the counterfactual world that produces recommendations when each user has changed the sensitive attribute value. To this end, we first borrow the Rubin-Neyman potential outcome framework to define average causal effects of sensitive attributes. Next, we show that removing causal effects of sensitive attributes is equal to average counterfactual fairness in CF. Then, we use the propensity re-weighting paradigm to estimate the average causal effects of sensitive attributes and formulate the estimated causal effects as an additional regularization term. To the best of our knowledge, we are one of the first few attempts to achieve counterfactual fairness from the causal effect estimation perspective in CF, which frees us from building sophisticated causal graphs. Finally, experiments on three real-world datasets show the superiority of our proposed model.

Generating human mobility trajectories is of great importance to solve the lack of large-scale trajectory data in numerous applications, which is caused by privacy concerns. However, existing mobility trajectory generation methods still require real-world human trajectories centrally collected as the training data, where there exists an inescapable risk of privacy leakage. To overcome this limitation, in this paper, we propose PateGail, a privacy-preserving imitation learning model to generate mobility trajectories, which utilizes the powerful generative adversary imitation learning model to simulate the decision-making process of humans. Further, in order to protect user privacy, we train this model collectively based on decentralized mobility data stored in user devices, where personal discriminators are trained locally to distinguish and reward the real and generated human trajectories. In the training process, only the generated trajectories and their rewards obtained based on personal discriminators are shared between the server and devices, whose privacy is further preserved by our proposed perturbation mechanisms with theoretical proof to satisfy differential privacy. Further, to better model the human decision-making process, we propose a novel aggregation mechanism of the rewards obtained from personal discriminators. We theoretically prove that under the reward obtained based on the aggregation mechanism, our proposed model maximizes the lower bound of the discounted total rewards of users. Extensive experiments show that the trajectories generated by our model are able to resemble real-world trajectories in terms of five key statistical metrics, outperforming state-of-the-art algorithms by over 48.03%. Furthermore, we demonstrate that the synthetic trajectories are able to efficiently support practical applications, including mobility prediction and location recommendation.

As mobile communication technologies advance, mobile networks become increasingly complex, and user requirements become increasingly diverse. To satisfy the diverse demands of users while improving the overall performance of the network system, the limited wireless network resources should be efficiently and dynamically allocated to them based on the magnitude of their demands and their relative location to the base stations. We separated the problem into four constrained subproblems, which we then solved using a safe reinforcement learning method. In addition, we design a reward mechanism to encourage agent cooperation in distributed training environments. We test our methodology in a simulated scenario with thousands of users and hundreds of base stations. According to experimental findings, our method guarantees that over 95% of user demands are satisfied while also maximizing the overall system throughput.

Short-video recommendation is one of the most important recommendation applications in today's industrial information systems. Compared with other recommendation tasks, the enormous amount of feedback is the most typical characteristic. Specifically, in short-video recommendation, the easiest-to-collect user feedback is theskipping behavior, which leads to two critical challenges for the recommendation model. First, the skipping behavior reflects implicit user preferences, and thus, it is challenging for interest extraction. Second, this kind of special feedback involves multiple objectives, such as total watching time and skipping rate, which is also very challenging. In this paper, we present our industrial solution in Kuaishou1, which serves billion-level users every day. Specifically, we deploy a feedback-aware encoding module that extracts user preferences, taking the impact of context into consideration. We further design a multi-objective prediction module which well distinguishes the relation and differences among different model objectives in the short-video recommendation. We conduct extensive online A/B tests, along with detailed and careful analysis, which verify the effectiveness of our solution.

Heterogeneous graph neural networks (HGNNs) have achieved remarkable development recently and exhibited superior performance in various tasks. However, recently HGNNs have been shown to have robustness weakness towards adversarial perturbations, which brings critical pitfalls for real applications, e.g. node classification and recommender systems. In particular, the transfer-based black-box attack is the most practical method to attack unknown models and poses a great threat to the reliability of HGNNs. In this work, we take the first step to explore the transferability of adversarial examples of HGNNs. Due to the overfitting of the source model, the adversarial perturbations generated by traditional methods usually exhibit unpromising transferability. To address this problem and boost adversarial transferability, we expect to seek common vulnerable directions of different models to attack. Inspired by the observation of the notable commonality of edge attention distribution between different HGNNs, we propose to guide the perturbation generation toward disrupting edge attention distribution. This edge attention-guided attack prioritizes the perturbation on edges that are more likely to be given common attention by different models, which benefits the transferability of adversarial perturbations. Finally, we develop two edge attention-guided attack methods towards heterogeneous relations tailored for HGNNs, called EA-FGSM and EA-PGD. Extensive experiments on six representative models and two datasets verify the effectiveness of our methods and form an unprecedented transfer robustness benchmark for HGNNs.

Prediction of couriers' delivery timely rates in advance is essential to the logistics industry, enabling companies to take preemptive measures to ensure the normal operation of delivery services. This becomes even more critical during anomaly conditions like the epidemic outbreak, during which couriers' delivery timely rate will decline markedly and fluctuates significantly. Existing studies pay less attention to the logistics scenario. Moreover, many works focusing on prediction tasks in anomaly scenarios fail to explicitly model abnormal events, e.g., treating external factors equally with other features, resulting in great information loss. Further, since some anomalous events occur infrequently, traditional data-driven methods perform poorly in these scenarios. To deal with them, we propose a deep spatial-temporal attention model, named DeepSTA. To be specific, to avoid information loss, we design an anomaly spatio-temporal learning module that employs a recurrent neural network to model incident information. Additionally, we utilize Node2vec to model correlations between road districts, and adopt graph neural networks and long short-term memory to capture the spatial-temporal dependencies of couriers. To tackle the issue of insufficient training data in abnormal circumstances, we propose an anomaly pattern attention module that adopts a memory network for couriers' anomaly feature patterns storage via attention mechanisms. The experiments on real-world logistics datasets during the COVID-19 outbreak in 2022 show the model outperforms the best baselines by 12.11% in MAE and 13.71% in MSE, demonstrating its superior performance over multiple competitive baselines.

For walking pedestrians, when they are blocked by obstacles or other pedestrians, they adjust their speeds and directions to avoid colliding with them, which is called collision avoidance behavior. This behavior is the most complex part of pedestrians' walking processes and its modeling and simulation are the keys to realistic crowd simulation, which serves as the foundation for various applications. However, most existing methods either lack the representation power to accurately model the complex collision behavior or do not model it explicitly, which leads to a poor level of realism of the simulation. To realize realistic crowd simulation, we propose to analyze, understand, and model the collision avoidance behavior in a data-driven way. First, to automatically detect collision avoidance behavior for further analysis, we propose a domain transformation algorithm that detects it by transforming the trajectories in the spatial domain into a new domain where the behavior is much more apparent and is thus easier to detect. The new domain also provides a new perspective for understanding collision avoidance behavior. Second, since there are no mature metrics to evaluate the level of realism, we propose a new evaluation metric based on the least-effort theory, which evaluates the realism of collision avoidance behavior by its physical and mental consumption. This evaluation metric also provides the foundation of modeling. Third, for realistic crowd simulation, we design a reinforcement learning model. It trains agents with our proposed reward function that models pedestrians' intrinsic needs of "reducing effort consumption'' and thus can guide agents to behave realistically when avoiding collisions. Extensive experiments show our model is 55.9% and 52.5% more realistic in collision avoidance behavior than the best baselines on two real-world datasets. We release our codes at https://github.com/tsinghua-fib-lab/TECRL.

Improving logistics efficiency is a challenging task in logistic systems, since planning the vehicle routes highly relies on the changing traffic conditions and diverse demand scenarios. However, most existing approaches either neglect the dynamic traffic environment or adopt manually designed rules, which fails to efficiently find a high-quality routing strategy. In this paper, we present a novel artificial intelligence (AI) based framework for logistic systems. This framework can simulate the spatio-temporal traffic conditions to form a dynamic environment in a data-driven manner. Under such a simulated environment, it adopts deep reinforcement learning techniques to intelligently generate the optimized routing strategy. Meanwhile, we also design an interactive frontend to visualize the simulated environment and routing strategies, which help operators evaluate the task performance. We will showcase the results of AI-based simulation and optimization in our demonstration.

Knowledge graph (KG) embedding is a fundamental task in natural language processing, and various methods have been proposed to explore semantic patterns in distinctive ways.In this paper, we propose to learn an ensemble by leveraging existing methods in a relation-aware manner.However, exploring these semantics using relation-aware ensemble leads to a much larger search space than general ensemble methods.To address this issue, we propose a dividesearch-combine algorithm RelEns-DSC that searches the relation-wise ensemble weights independently.This algorithm has the same computation cost as general ensemble methods but with much better performance.Experimental results on benchmark datasets demonstrate the effectiveness of the proposed method in efficiently searching relation-aware ensemble weights and achieving state-of-the-art embedding performance.The code is public at https: //github.com/LARS-research/RelEns. 1

High-definition (HD) maps play an essential role in autonomous driving. However, producing HD map needs huge amount of manual annotations and is thus labor intensive and costly, which limits the widespread use of HD map. To improve the productivity and reduce cost, extensive studies have explored automation of HD map production. Existing studies primarily focus on constructing vectorized map elements from vehicle sensing images and point clouds. However, the follow-up procedure of extracting traffic semantics based on vectorized map elements is lack of study, though it is laborious and costly as well. In this paper, we focus on the automation of inferring traffic light controls for HD map production. To be specific, we aim at associating traffic lights with their controlled roads based on vectorized map data. This problem is not trivial in that: 1) the placement of traffic light contrastive to road varies considerably from scene to scene; 2) even if the placement of traffic lights and roads are similar, the road network layout has great influence on the traffic light controls. To tackle the above challenges, we propose a Heterogeneous Interaction model with Stacked Transformers (HIST) that learns representation from vectorized map elements and encodes contextual information via heterogeneous interactions among different types of map elements. We conduct extensive experiments in major cities of China to validate the efficacy of HIST. Results show HIST achieves accuracy ranging from 96.03% to 98.85% in different cities. We further deploy HIST on the HD map production line at AMAP. By incorporating a rule-based confidence system, the whole system achieves the performance with accuracy > 99.9% and automation rate > 85%, which meets the industrial level quality requirement and saves vast amount of human labor.

Accurately predicting base station traffic volumes and understanding mobile traffic patterns is essential for smart city development, enabling efficient resource allocation and ensuring high-quality communication services. However, existing works have limitations in capturing spatial information, though the surrounding environment plays a critical role in mobile traffic prediction. In this paper, we utilize a spatial knowledge graph to represent spatial information and add important urban components to augment it making it a more effective tool for capturing environmental information. we further propose a multi-relational knowledge graph convolutional network model for mobile traffic prediction, which consists of three parts. The environmental context modelling captures spatial information from the augmented spatial knowledge graph using tucker decomposition and relational graph convolutional network. The semantic relationship modelling extracts semantic relationships between base stations and employs transformer and causal convolution to capture temporal features. The inter-attentional fusion modelling utilizes the self-attention mechanism to further capture base station relationships and predict future traffic volumes. Extensive experiments demonstrate that our proposed model significantly outperforms the state-of-the-art models by over 10% in mobile traffic prediction. The code is available at https://github.com/tsinghua-fiblab/Mobile-Traffic-Prediction-sigspatial23

Built environment supports all the daily activities and shapes our health. Leveraging informative street view imagery, previous research has established the profound correlation between the built environment and chronic, non-communicable diseases; however, predicting the exposure risk of infectious diseases remains largely unexplored. The person-to-person contacts and interactions contribute to the complexity of infectious disease, which is inherently different from non-communicable diseases. Besides, the complex relationships between street view imagery and epidemic exposure also hinder accurate predictions. To address these problems, we construct a regional mobility graph informed by the gravity model, based on which we propose a transmission-aware graph neural network (GNN) to capture disease transmission patterns arising from human mobility. Experiments show that the proposed model significantly outperforms baseline models by 8.54% in weighted F1, shedding light on a low-cost, scalable approach to assess epidemic exposure risks from street view imagery.

Traffic congestion has a negative impact on our daily life. Predicting the trend of traffic congestion can provide a valuable guideline to address such problems. Most existing approaches focus on the tasks of predicting traffic volume or traffic speed, which do not effectively address the challenges of traffic congestion prediction. First, traffic congestion exhibits daily and weekly temporal patterns, but these patterns are not strictly the same, which indicates complicated long-term periodicity. Second, traffic congestion sparsely distributes over different periods of time, which leads to complex short-term and mid-term temporal dependencies. Third, since traffic congestion will propagate to adjacent road segments over time, it exhibits complex spatio-temporal correlations. To address them, we propose a periodic shift and event-aware spatio-temporal graph convolutional network for traffic congestion prediction. Specifically, we propose to capture the differences and similarities of long-term periodic temporal patterns to handle the complicated long-term periodicity. To effectively capture short-term and mid-term temporal dependencies, we regard a continuous time sequence of the congested condition as a traffic congestion event, and then adopt the widely-used long short-term memory model to learn the sequential dependencies of traffic congestion events. Finally, we integrate the graph convolutional network into the modeling of temporal dependencies to capture the complex spatio-temporal correlations. Extensive experiments demonstrate the superiority of our model. In addition, we deploy our model in production at Amap, and it achieves great performance improvement in terms of the F1-score compared to the production baseline. This confirms that our model is a practical solution for real-world congestion prediction services.

Site selection determines optimal locations for new stores, which is of crucial importance for business success and urban development. Especially, the wide application of artificial intelligence with multi-source urban data makes intelligent site selection promising. Nevertheless, existing data-driven approaches heavily rely on feature engineering, which cannot take the complex relationships as well as the diverse influences of various semantics among data into consideration. Further, most approaches fail to reveal underlying factors for site decisions. To get rid of the dilemma, in this work, leveraging the knowledge graph (KG) technique, we propose a knowledge-driven model for site selection, short for KnowSite. Specifically, by empowering rich semantics in KG, we firstly construct an urban KG (UrbanKG) for site selection knowledge discovery with cities' key elements and complex relationships captured. Based on UrbanKG, we apply pre-training for semantic representations, and then design a generalized encoder-decoder structure for site decisions. KnowSite designs a graph neural network based encoder to adaptively model diverse influences, and further builds a relation path based decoder revealing the reasons behind site decisions. Extensive experiments on two datasets demonstrate that KnowSite outperforms representative baselines by more than 9% on precision. Moreover, KnowSite provides intuitive and convincing explanations for site decisions and sheds light on the site selection understanding.

Location prediction acts as a fundamental service in today's location-based information platform, which helps users access locations satisfying their demands, improving both user experience and platform profit. Since users with unambiguous demands prefer specific locations while users with compound demands consider first regions and then specific locations, it is necessary to model multi-grained user preferences at different geographical scales. However, most of the existing works concentrate on user preferences at the location-scale only, which can not understand users traveling behaviors thoroughly. In this paper, we propose to model both the fine-grained user preferences at the location scale and the coarsegrained user preferences at the region scale. Specifically, the proposed model harnesses the efficient information extraction power of graph neural networks. Moreover, the proposed geographical calibration method also helps to capture multi-grained user preferences accurately. Experiments on datasets of two very large cities demonstrate the significant performance improvement using our approach over state-of-the-art models. We also conduct experiments to further demonstrate the effectiveness of each component in the proposed model. Source codes of this paper are available at https://github.com/tsinghua-fib-lab/SIGSPATIAL-MMGUP/.

With the increasing prevalence of infectious diseases like COVID-19, there is a growing interest in modeling and predicting their transmission. Leveraging the wealth of mobile trajectory data collected through advanced localization and mobile communication techniques, numerous approaches have been proposed to predict the spatial spread of infectious diseases based on human mobility dynamics characterized by microscopic user contact graphs or macroscopic population flow graphs. However, existing pure macroscopic and microscopic models have limitations in terms of modeling capabilities or in protecting user privacy. Thus, in this study, we present a Multi-scale Spatial Disease prediction Network (MSDNet) for predicting the spatial spread of infectious diseases. The model predicts the spread of infectious diseases using a macromicro collaborative approach by combining the temporal and spatial characteristics of the macroscopic information in the population flow graph and the microscopic information in the user contact graph. To understand the coupling between human mobility and infectious disease transmission, we propose a loss term that combines infectious disease spread dynamics and modeling of infectious disease parameters that can achieve stable adaptation to key characteristics of infectious diseases even when human mobility is affected by policy measures such as travel restrictions. Extensive experimental results show the MSDNet model's superiority for epidemic prediction on graph networks using macro-micro collaboration, achieving a 15%-20% improvement in terms of RMSE and a 15%-30% improvement in terms of SMAPE compared to existing baseline models. In addition, we predict infectious disease parameters under changes in human mobility, and the results show that MSDNet could effectively distinguish between human mobility and infectious disease characteristics, achieving a relative improvement of 76% in terms of RMSE and 80% in terms of SMAPE in predicting infectious disease parameters under changes in human mobility.

Frequent traffic congestion has a detrimental effect on our travel experience and the overall quality of urban life. Accurate prediction of traffic congestion plays a pivotal role in alleviating the congestion problem. However, existing traffic prediction approaches primarily focus on extracting its local changing patterns, overlooking the importance of incorporating global dynamic patterns. This presents three challenges: 1) Complicated spatial and temporal information exists in local (microscopic) traffic patterns; 2) The propagation and dissipation patterns of global (macroscopic) traffic congestion exhibit complex dynamics across time and space; 3) Modeling the interactions between macro and micro changing patterns of congestion remains unknown. In this paper, we present a novel framework for traffic congestion prediction that integrates microscopic and macroscopic cross-scale spatiotemporal modeling. Our approach utilizes contagion dynamics to characterize congestion propagation and recovery at the network-wide scale. Additionally, we employ a spatio-temporal graph neural network to capture local traffic patterns. A key contribution is the introduction of a differentiable micro-macro transformation mechanism, enabling the aggregation of microscopic states into macroscopic ones in a differentiable manner during model training. Further, we utilize the knowledge derived from macro contagion dynamics to constrain the micro traffic patterns by employing the physics-informed neural network. Experiments on three real-world datasets of traffic congestion demonstrate that our prediction model consistently outperforms the state-of-the-art baselines.

Although generative AI has been successful in many areas, its ability to model geospatial data is still underexplored. Urban flow, a typical kind of geospatial data, is critical for a wide range of applications from public safety and traffic management to urban planning. Existing studies mostly focus on predictive modeling of urban flow that predicts the future flow based on historical flow data, which may be unavailable in data-sparse areas or newly planned regions. Some other studies aim to predict OD flow among regions but they fail to model dynamic changes of urban flow over time. In this work, we study a new problem of urban flow generation that generates dynamic urban flow for regions without historical flow data. To capture the effect of multiple factors on urban flow, such as region features and urban environment, we employ diffusion model to generate urban flow for regions under different conditions. We first construct an urban knowledge graph (UKG) to model the urban environment and relationships between regions, based on which we design a knowledge-enhanced spatio-temporal diffusion model (KSTDiff) to generate urban flow for each region. Specifically, to accurately generate urban flow for regions with different flow volumes, we design a novel diffusion process guided by a volume estimator, which is learnable and customized for each region. Moreover, we propose a knowledge-enhanced denoising network to capture the spatio-temporal dependencies of urban flow as well as the impact of urban environment in the denoising process. Extensive experiments on four real-world datasets validate the superiority of our model over state-of-the-art baselines in urban flow generation. Further in-depth studies demonstrate the utility of generated urban flow data and the ability of our model for long-term flow generation and urban flow prediction. Our code is released at: https://github.com/tsinghua-fib-lab/KSTDiff-Urban-flow-generation.

Understanding the impact of COVID-19 on urban life rhythms is crucial for accelerating the return-to-normal progress and envisioning more resilient and inclusive cities. While previous studies either depended on small-scale surveys or focused on the response to initial lockdowns, this paper uses large-scale location service data to systematically analyze the urban mobility behavior changes across three distinct phases of the pandemic, i.e., pre-pandemic, lockdown, and reopen. Our analyses reveal two typical patterns that govern the mobility behavior changes in most urban venues: daily life-centered urban venues go through smaller mobility drops during the lockdown and more rapid recovery after reopening, while work-centered urban venues suffer from more significant mobility drops that are likely to persist even after reopening. Such mobility behavior changes exert deeper impacts on the underlying social fabric, where the level of mobility reduction is positively correlated with the experienced segregation at that urban venue. Therefore, urban venues undergoing more mobility reduction are also more filled with people from homogeneous socio-demographic backgrounds. Moreover, mobility behavior changes display significant heterogeneity across geographical regions, which can be largely explained by the partisan inclination at the state level. Our study shows the vast potential of location service data in deriving a timely and comprehensive understanding of the social dynamic in urban space, which is valuable for informing the gradual transition back to the normal lifestyle in a “post-pandemic era”.

Spatio-temporal point process (STPP) is a stochastic collection of events accompanied with time and space. Due to computational complexities, existing solutions for STPPs compromise with conditional independence between time and space, which consider the temporal and spatial distributions separately. The failure to model the joint distribution leads to limited capacities in characterizing the spatio-temporal entangled interactions given past events. In this work, we propose a novel parameterization framework for STPPs, which leverages diffusion models to learn complex spatio-temporal joint distributions. We decompose the learning of the target joint distribution into multiple steps, where each step can be faithfully described by a Gaussian distribution. To enhance the learning of each step, an elaborated spatio-temporal co-attention module is proposed to capture the interdependence between the event time and space adaptively. For the first time, we break the restrictions on spatio-temporal dependencies in existing solutions, and enable a flexible and accurate modeling paradigm for STPPs. Extensive experiments from a wide range of fields, such as epidemiology, seismology, crime, and urban mobility, demonstrate that our framework outperforms the state-of-the-art baselines remarkably. Further in-depth analyses validate its ability to capture spatio-temporal interactions, which can learn adaptively for different scenarios. The datasets and source code are available online: https://github.com/tsinghua-fib-lab/Spatio-temporal-Diffusion-Point-Processes.

The two-dimensional bin packing problem (2DBP) is a critical optimization problem in the furniture production and glass cutting industries, where the objective is to cut smaller-sized items from a minimum number of large standard-sized raw materials. In practice, factories manufacture hundreds of customer orders (sets of items) every day, and to relieve pressure in management, a common practice is to group the orders into batches for production, ensuring that items from one order are in the same batch instead of scattered across the production line. In this work, we formulate this problem as the grouped 2D bin packing problem, a bi-level problem where the upper level partitions orders into groups and the lower level solves 2DBP for items in each group. The main challenges are (1) the coupled optimization of upper and lower levels and (2) the high computational efficiency required for practical application. To tackle these challenges, we propose an iteration-based hierarchical reinforcement learning framework, which can learn to solve the optimization problem in a data-driven way and provide fast online performance after offline training. Extensive experiments demonstrate that our method not only achieves the best performance compared to all baselines but is also robust to changes in dataset distribution and problem constraints. Finally, we deployed our method in the ARROW Home factory in China, resulting in a 4.1% reduction in raw material costs. We have released the source code and datasets to facilitate future research.

Pick-up and delivery (PD) services such as online food ordering are playing an increasingly important role in serving people's daily demands. Accurate PD route prediction (PDRP) is important for service providers to efficiently schedule riders to improve service quality. It is crucial to model the decision-making process behind the route choice of riders for PDRP. Recent years have witnessed the success of utilizing imitation learning (IL) to model user decision-making process. Therefore, we propose to deploy an IL framework to solve the PDRP problem. However, there still exist three main challenges: (1) the rider's route decision is affected by multi-source and heterogeneous features and the complex relationships among these features make it hard to explore how they influence the rider's route decision-making; (2) the large route decision-making space make it easy to explore and predict unreasonable routes; (3) the rider's personalized preference is important in modeling the route decision-making process but cannot be fully explored. To tackle the above challenges, we propose ILRoute, a Graph-based imitation learning method for PDRP. ILRoute utilizes a multi-graph neural network (multi-GNN) to extract the multi-source and heterogeneous features and model their complex relationships. To address the large route decision-making space, ILRoute introduces a mobility regularity-aware constraint as prior route choice knowledge to reduce the exploration route decision-making space. To model the personalized preferences of the rider, ILRoute utilizes a personalized constraint mechanism to enhance the personalization of the rider's route decision-making process. Offline experiments conducted on three real-world datasets and online comparisons demonstrate the superiority of our proposed model.

Recent advancements in reinforcement learning have witnessed remarkable achievements by intelligent agents ranging from game-playing to industrial applications. Of particular interest is the area of multi-agent reinforcement learning (MARL), which holds significant potential for real-world scenarios. However, typical MARL methods are limited in their ability to handle tens of agents, leaving scenarios with up to hundreds or even thousands of agents almost unexplored. The scaling up of the number of agents presents two primary challenges: (1) agent-agent interactions are crucial in multi-agent systems while the number of interactions grows quadratically with the number of agents, resulting in substantial computational complexity and difficulty in strategies-learning; (2) the strengths of interactions among agents exhibit variations both across agents and over time, making it difficult to precisely model such interactions. In this paper, we propose a novel approach named Graph Attention Mean Field (GAT-MF). By converting agent-agent interactions into interactions between each agent and a weighted mean field, we achieve a substantial reduction in computational complexity. The proposed method offers a precise modeling of interaction dynamics with mathematical proofs of its correctness. Additionally, we design a graph attention mechanism to automatically capture the diverse and time-varying strengths of interactions, ensuring an accurate representation of agent interactions. Through extensive experimentation conducted in both manual and real-world scenarios involving over 3000 agents, we validate the efficacy of our method. The results demonstrate that our method outperforms the best baseline method with a remarkable improvement of 42.7%. Furthermore, our method saves 86.4% training time and 19.2% GPU memory compared to the best baseline method. For reproducibility, our source codes and data are available at https://github.com/tsinghua-fib-lab/Large-Scale-MARL-GATMF.

With the rapid development of the cellular network, network planning is increasingly important. Generating large-scale urban cellular traffic contributes to network planning via simulating the behaviors of the planned network. Existing methods fail in simulating the long-term temporal behaviors of cellular traffic while cannot model the influences of the urban environment on the cellular networks. We propose a knowledge-enhanced GAN with multi-periodic patterns to generate large-scale cellular traffic based on the urban environment. First, we design a GAN model to simulate the multi-periodic patterns and long-term aperiodic temporal dynamics of cellular traffic via learning the daily patterns, weekly patterns, and residual traffic between long-term traffic and periodic patterns step by step. Then, we leverage urban knowledge to enhance traffic generation via constructing a knowledge graph containing multiple factors affecting cellular traffic in the surrounding urban environment. Finally, we evaluate our model on a real cellular traffic dataset. Our proposed model outperforms three state-of-art generation models by over 32.77%, and the urban knowledge enhancement improves the performance of our model by 4.71%. Moreover, our model achieves good generalization and robustness in generating traffic for urban cellular networks without training data in the surrounding areas.

Living needs refer to the various needs in human's daily lives for survival and well-being, including food, housing, entertainment, etc. At life service platforms that connect users to service providers, such as Meituan, the problem of living needs prediction is fundamental as it helps understand users and boost various downstream applications such as personalized recommendation. However, the problem has not been well explored and is faced with two critical challenges. First, the needs are naturally connected to specific locations and times, suffering from complex impacts from the spatiotemporal context. Second, there is a significant gap between users' actual living needs and their historical records on the platform. To address these two challenges, we design a system of living NEeds predictiON named NEON, consisting of three phases: feature mining, feature fusion and multi-task prediction. In the feature mining phase, we carefully extract individual-level user features for spatiotemporal modeling, and aggregated-level behavioral features for enriching data, which serve as the basis for addressing two challenges, respectively. Further, in the feature fusion phase, we propose a neural network that effectively fuses two parts of features into the user representation. Moreover, we design a multitask prediction phase, where the auxiliary task of needs-meeting way prediction can enhance the modeling of spatiotemporal context. Extensive offline evaluations verify that our NEON system can effectively predict users' living needs. Furthermore, we deploy NEON into Meituan's algorithm engine and evaluate how it enhances the three downstream prediction applications, via large-scale online A/B testing. As a representative result, deploying our system leads to a 1.886% increase w.r.t. CTCVR in Meituan homepage recommendation. The results demonstrate NEON's effectiveness in predicting fine-grained user needs, needs-meeting way, and potential needs, highlighting the immense application value of NEON.

Learning the underlying slow and fast dynamics of a system is instrumental for many practical applications related to the system. However, existing approaches are limited in discovering the appropriate time scale to separate the slow and fast variables and effectively learning their dynamics based on correct-dimensional representation vectors. In this paper, we introduce a framework that effectively learns slow and fast system dynamics in an integrated manner. We propose a novel intrinsic dimensionality (ID) driven learning method based on a time-lagged autoencoder framework to identify appropriate time scales to separate slow and fast variables and their IDs simultaneously. Further, we propose an integrated framework to concurrently learn the system's slow and fast dynamics, which is able to integrate prior knowledge of time scale and IDs and model the complex coupled slow and fast variables. Extensive experimental results on two representative dynamical systems show that our proposed framework is able to efficiently learn slow and fast system dynamics. Specifically, the long-time prediction performance is able to be improved by 36% on average compared with four representative baselines based on our proposed framework. Furthermore, our proposed system is able to extract interpretable slow and fast dynamics highly correlated with the known slow and fast variables in the dynamical systems. Our codes and datasets are open-sourced at: https://github.com/tsinghua-fib-lab/SlowFastSeparation.

Human trajectories, reflecting people's travel patterns and the range of activities, are crucial for the applications like urban planning and epidemic control. However, the real-world human trajectory data tends to be limited by user privacy or device acquisition issues, leading to its insufficient quality to support the above applications. Hence, generating human trajectory data is a crucial but challenging task, which suffers from the following two critical challenges: 1) how to capture the user distribution in human trajectories (group view), and 2) how to model the complex mobility patterns of each user trajectory (individual view). In this paper, we propose a novel human trajectories generator (named VOLUNTEER), consisting of a user VAE and a trajectory VAE, to address the above challenges. Specifically, in the user VAE, we propose to learn the user distribution with all human trajectories from a group view. In the trajectory VAE, from the individual view, we model the complex mobility patterns by decoupling travel time and dwell time to accurately simulate individual trajectories. Extensive experiments on two real-world datasets show the superiority of our model over the state-of-the-art baselines. Further application analysis in the industrial system also demonstrates the effectiveness of our model.

Understanding and characterizing the vulnerability of urban infrastructures, which refers to the engineering facilities essential for the regular running of cities and that exist naturally in the form of networks, is of great value to us. Potential applications include protecting fragile facilities and designing robust topologies, etc. Due to the strong correlation between different topological characteristics and infrastructure vulnerability and their complicated evolution mechanisms, some heuristic and machine assisted analysis fall short in addressing such a scenario. In this paper, we model the interdependent network as a heterogeneous graph and propose a system based on graph neural network with reinforcement learning, which can be trained on real-world data, to characterize the vulnerability of the city system accurately. The presented system leverages deep learning techniques to understand and analyze the heterogeneous graph, which enables us to capture the risk of cascade failure and discover vulnerable infrastructures of cities. Extensive experiments with various requests demonstrate not only the expressive power of our system but also transferring ability and necessity of the specific components. All source codes and models including those that can reproduce all figures analyzed in this work are publicly available at this link: https://github.com/tsinghua-fib-lab/KDD2023-ID546-UrbanInfra.

Automated Machine Learning (AutoML) techniques have recently been introduced to design Collaborative Filtering (CF) models in a data-specific manner. However, existing works either search architectures or hyperparameters while ignoring the fact they are intrinsically related and should be considered together. This motivates us to consider a joint hyperparameter and architecture search method to design CF models. However, this is not easy because of the large search space and high evaluation cost. To solve these challenges, we reduce the space by screening out usefulness hyperparameter choices through a comprehensive understanding of individual hyperparameters. Next, we propose a two-stage search algorithm to find proper configurations from the reduced space. In the first stage, we leverage knowledge from subsampled datasets to reduce evaluation costs; in the second stage, we efficiently fine-tune top candidate models on the whole dataset. Extensive experiments on real-world datasets show better performance can be achieved compared with both hand-designed and previous searched models. Besides, ablation and case studies demonstrate the effectiveness of our search framework.

The problem of cellular traffic generation in cities without historical traffic data is critical and urgently needs to be solved to assist 5G base station deployments in mobile networks. In this paper, we propose ADAPTIVE, a deep transfer learning framework for city-scale cellular traffic generation through the urban knowledge graph. ADAPTIVE leverages historical data from other cities that have deployed 5G networks to assist cities that are newly deploying 5G networks through deep transfer learning. Specifically, ADAPTIVE can align the representations of base stations in the target city and source city while considering the environmental factors of cities, spatial and environmental contextual relations between base stations, and traffic temporal patterns at base stations. We next design a feature-enhanced generative adversarial network, which is trained based on the historical traffic data and representations of base stations in the source city. By feeding the aligned target city's base station representations into the trained model, we can then obtain the generated traffic data for the target city. Extensive experiments on real-world cellular traffic datasets show that ADAPTIVE generally outperforms state-of-the-art baselines by more than 40% in terms of Jensen-Shannon divergence and root-mean-square error. Also, ADAPTIVE has strong robustness based on the results of various cross-city experiments. ADAPTIVE has been successfully deployed on the 'Jiutian' Artificial Intelligence Platform of China Mobile to support cellular traffic generation and assist in the construction and operation of mobile networks.

Millions of slum dwellers suffer from poor accessibility to urban services due to inadequate road infrastructure within slums, and road planning for slums is critical to the sustainable development of cities. Existing re-blocking or heuristic methods are either time-consuming which cannot generalize to different slums, or yield sub-optimal road plans in terms of accessibility and construction costs. In this paper, we present a deep reinforcement learning based approach to automatically layout roads for slums. We propose a generic graph model to capture the topological structure of a slum, and devise a novel graph neural network to select locations for the planned roads. Through masked policy optimization, our model can generate road plans that connect places in a slum at minimal construction costs. Extensive experiments on real-world slums in different countries verify the effectiveness of our model, which can significantly improve accessibility by 14.3% against existing baseline methods. Further investigations on transferring across different tasks demonstrate that our model can master road planning skills in simple scenarios and adapt them to much more complicated ones, indicating the potential of applying our model in real-world slum upgrading. The code and data are available at https://github.com/tsinghua-fib-lab/road-planning-for-slums.

Recently multi-modal recommender systems have been widely applied in real scenarios such as e-commerce businesses. Existing multi-modal recommendation methods exploit the multi-modal content of items as auxiliary information and fuse them to boost performance. Despite the superior performance achieved by multi-modal recommendation models, there's currently no understanding of their robustness to adversarial attacks. In this work, we first identify the vulnerability of existing multi-modal recommendation models. Next, we show the key reason for such vulnerability is modality imbalance, i.e., the prediction score margin between positive and negative samples in the sensitive modality will drop dramatically facing adversarial attacks and fail to be compensated by other modalities. Finally, based on this finding we propose a novel defense method to enhance the robustness of multi-modal recommendation models through modality balancing. Specifically, we first adopt an embedding distillation to obtain a pair of content-similar but prediction-different item embeddings in the sensitive modality and calculate the score margin reflecting the modality vulnerability. Then we optimize the model to utilize the score margin between positive and negative samples in other modalities to compensate for the vulnerability. The proposed method can serve as a plug-and-play module and is flexible to be applied to a wide range of multi-modal recommendation models. Extensive experiments on two real-world datasets demonstrate that our method significantly improves the robustness of multi-modal recommendation models with nearly no performance degradation on clean data.

Digital Twin brings a new realization approach to the modeling of mobile networks. Mobile networks, as complex systems comprising multiple components, such as mobile users, base stations, and wireless environments, have intricate interactions and relationships with each other. By creating a virtual replica of each physical mobile network entity in a virtual space, we build a scalable digital twin system for mobile networks with generative AI. The system can interact with multiple optimizers to evaluate and display real-time simulation results. A companion video can be accessed using the link below. https://youtu.be/xtcBIXPzvkc

As hyper-parameters are ubiquitous and can significantly affect the model performance, hyper-parameter optimization is extremely important in machine learning. In this paper, we consider a sub-class of hyper-parameter optimization problems, where the hyper-gradients are not available. Such problems frequently appear when the performance metric is non-differentiable or the hyper-parameter is not continuous. However, existing algorithms, like Bayesian optimization and reinforcement learning, often get trapped in local optimals with poor performance. To address the above limitations, we propose to use cubic regularization to accelerate convergence and avoid saddle points. First, we adopt stochastic relaxation, which allows obtaining gradient and Hessian information without hyper-gradients. Then, we exploit the rich curvature information by cubic regularization. Theoretically, we prove that the proposed method can converge to approximate second-order stationary points, and the convergence is also guaranteed when the lower-level problem is inexactly solved. Experiments on synthetic and real-world data demonstrate the effectiveness of our proposed method.

Sequential recommendation is one of the most important tasks in recommender systems, which aims to recommend the next interacted item with historical behaviors as input. Traditional sequential recommendation always mainly considers the collected positive feedback such as click, purchase, etc. However, in short-video platforms such as TikTok, video viewing behavior may not always represent positive feedback. Specifically, the videos are played automatically, and users passively receive the recommended videos. In this new scenario, users passively express negative feedback by skipping over videos they do not like, which provides valuable information about their preferences. Different from the negative feedback studied in traditional recommender systems, this passive-negative feedback can reflect users’ interests and serve as an important supervision signal in extracting users’ preferences. Therefore, it is essential to carefully design and utilize it in this novel recommendation scenario. In this work, we first conduct analyses based on a large-scale real-world short-video behavior dataset and illustrate the significance of leveraging passive feedback. We then propose a novel method that deploys the sub-interest encoder, which incorporates positive feedback and passive-negative feedback as supervision signals to learn the user’s current active sub-interest. Moreover, we introduce an adaptive fusion layer to integrate various sub-interests effectively. To enhance the robustness of our model, we then introduce a multi-task learning module to simultaneously optimize two kinds of feedback – passive-negative feedback and traditional randomly-sampled negative feedback. The experiments on two large-scale datasets verify that the proposed method can significantly outperform state-of-the-art approaches. The code is released at https://github.com/tsinghua-fib-lab/RecSys2023-SINE to benefit the community.

Graph Neural Network (GNN)-based models have become the mainstream approach for recommender systems. Despite the effectiveness, they are still suffering from the cold-start problem, i.e., recommend for few-interaction items. Existing GNN-based recommendation models to address the cold-start problem mainly focus on utilizing auxiliary features of users and items, leaving the user-item interactions under-utilized. However, embeddings distributions of cold and warm items are still largely different, since cold items' embeddings are learned from lower-popularity interactions, while warm items' embeddings are from higher-popularity interactions. Thus, there is a seesaw phenomenon, where the recommendation performance for the cold and warm items cannot be improved simultaneously. To this end, we proposed a Uncertainty-aware Consistency learning framework for Cold-start item recommendation (shorten as UCC) solely based on user-item interactions. Under this framework, we train the teacher model (generator) and student model (recommender) with consistency learning, to ensure the cold items with additionally generated low-uncertainty interactions can have similar distribution with the warm items. Therefore, the proposed framework improves the recommendation of cold and warm items at the same time, without hurting any one of them. Extensive experiments on benchmark datasets demonstrate that our proposed method significantly outperforms state-of-the-art methods on both warm and cold items, with an average performance improvement of 27.6%.

Recent years have witnessed the rapid development of online micro-video platforms, in which the recommender system plays an essential role in overcoming the information overloading problem and providing personalized content for users. Although some progress has been achieved in the micro-video recommendation, there are still some limitations in learning the representations of user interests and video features. Specifically, the user modeling in existing works is performed at a coarse-grained level, i.e., video level. However, in micro-video recommendation, the user feedback is at a continuous form---users can skip over a video at each frame---which reveals fine-grained user preferences. In this work, we approach the problem of learning fine-grained user preferences for micro-video recommendation by first collecting two real-world datasets. To address the challenges of preference modeling and weak supervision signal, we propose a solution named FRAME (short for Fine-gRAined preference-modeling for Micro-video rEcommendation). Specifically, we first adopt visual feature extraction and transformation to maintain the fine-grained video embeddings. We then propose graph convolution layers to learn the user preference from complex and fine-grained user-clip relations, and hybrid-supervision objectives for enhancing the supervision signal. The experimental results on two collected real-world datasets demonstrate the effectiveness of our proposed model. We release the datasets and codes in https://github.com/tsinghua-fib-lab/FRAME, which we believe can benefit the community.

Daily activity data that records individuals’ various types of activities in daily life are widely used in many applications such as activity scheduling, activity recommendation, and policymaking. Though with high value, its accessibility is limited due to high collection costs and potential privacy issues. Therefore, simulating human activities to produce massive high-quality data is of great importance to benefit practical applications. However, existing solutions, including rule-based methods with simplified assumptions of human behavior and data-driven methods directly fitting real-world data, both cannot fully qualify for matching reality. In this paper, motivated by the classic psychological theory, Maslow’s need theory describing human motivation, we propose a knowledge-driven simulation framework based on generative adversarial imitation learning. To enhance the fidelity and utility of the generated activity data, our core idea is to model the evolution of human needs as the underlying mechanism that drives activity generation in the simulation model. Specifically, this is achieved by a hierarchical model structure that disentangles different need levels, and the use of neural stochastic differential equations that successfully captures piecewise-continuous characteristics of need dynamics. Extensive experiments demonstrate that our framework outperforms the state-of-the-art baselines in terms of data fidelity and utility. Besides, we present the insightful interpretability of the need modeling. The code is available at https://github.com/tsinghua-fib-lab/Activity-Simulation-SAND.

In the information-overloaded era of the Web, recommender systems that provide personalized content filtering are now the mainstream portal for users to access Web information. Recommender systems deploy machine learning models to learn users’ preferences from collected historical data, leading to more centralized recommendation results due to the feedback loop. As a result, it will harm the ranking of content outside the narrowed scope and limit the options seen by users. In this work, we first conduct data analysis from a graph view to observe that the users’ feedback is restricted to limited items, verifying the phenomenon of centralized recommendation. We further develop a general simulation framework to derive the procedure of the recommender system, including data collection, model learning, and item exposure, which forms a loop. To address the filter bubble issue under the feedback loop, we then propose a general and easy-to-use reinforcement learning-based method, which can adaptively select few but effective connections between nodes from different communities as the exposure list. We conduct extensive experiments in the simulation framework based on large-scale real-world datasets. The results demonstrate that our proposed reinforcement learning-based control method can serve as an effective solution to alleviate the filter bubble and the separated communities induced by it. We believe the proposed framework of controllable recommendation in this work can inspire not only the researchers of recommender systems, but also a broader community concerned with artificial intelligence algorithms’ impact on humanity, especially for those vulnerable populations on the Web.

Accurate user interest modeling is vital for recommendation scenarios. One of the effective solutions is the sequential recommendation that relies on click behaviors, but this is not elegant in the video feed recommendation where users are passive in receiving the streaming contents and return skip or no-skip behaviors. Here skip and no-skip behaviors can be treated as negative and positive feedback, respectively. With the mixture of positive and negative feedback, it is challenging to capture the transition pattern of behavioral sequence. To do so, FeedRec has exploited a shared vanilla Transformer, which may be inelegant because head interaction of multi-heads attention does not consider different types of feedback. In this paper, we propose Dual-interest Factorization-heads Attention for Sequential Recommendation (short for DFAR) consisting of feedback-aware encoding layer, dual-interest disentangling layer and prediction layer. In the feedback-aware encoding layer, we first suppose each head of multi-heads attention can capture specific feedback relations. Then we further propose factorization-heads attention which can mask specific head interaction and inject feedback information so as to factorize the relation between different types of feedback. Additionally, we propose a dual-interest disentangling layer to decouple positive and negative interests before performing disentanglement on their representations. Finally, we evolve the positive and negative interests by corresponding towers whose outputs are contrastive by BPR loss. Experiments on two real-world datasets show the superiority of our proposed method against state-of-the-art baselines. Further ablation study and visualization also sustain its effectiveness. We release the source code here: https://github.com/tsinghua-fib-lab/WWW2023-DFAR.

Monitoring sustainable development goals requires accurate and timely socioeconomic statistics, while ubiquitous and frequently-updated urban imagery in web like satellite/street view images has emerged as an important source for socioeconomic prediction. Especially, recent studies turn to self-supervised contrastive learning with manually designed similarity metrics for urban imagery representation learning and further socioeconomic prediction, which however suffers from effectiveness and robustness issues. To address such issues, in this paper, we propose a Knowledge-infused Contrastive Learning (KnowCL) model for urban imagery-based socioeconomic prediction. Specifically, we firstly introduce knowledge graph (KG) to effectively model the urban knowledge in spatiality, mobility, etc., and then build neural network based encoders to learn representations of an urban image in associated semantic and visual spaces, respectively. Finally, we design a cross-modality based contrastive learning framework with a novel image-KG contrastive loss, which maximizes the mutual information between semantic and visual representations for knowledge infusion. Extensive experiments of applying the learnt visual representations for socioeconomic prediction on three datasets demonstrate the superior performance of KnowCL with over 30% improvements on R2 compared with baselines. Especially, our proposed KnowCL model can apply to both satellite and street imagery with both effectiveness and transferability achieved, which provides insights into urban imagery-based socioeconomic prediction.

Graph Neural Network (GNN) based social recommendation models improve the prediction accuracy of user preference by leveraging GNN in exploiting preference similarity contained in social relations. However, in terms of both effectiveness and efficiency of recommendation, a large portion of social relations can be redundant or even noisy, e.g., it is quite normal that friends share no preference in a certain domain. Existing models do not fully solve this problem of relation redundancy and noise, as they directly characterize social influence over the full social network. In this paper, we instead propose to improve graph based social recommendation by only retaining the informative social relations to ensure an efficient and effective influence diffusion, i.e., graph denoising. Our designed denoising method is preference-guided to model social relation confidence and benefits user preference learning in return by providing a denoised but more informative social graph for recommendation models. Moreover, to avoid interference of noisy social relations, it designs a self-correcting curriculum learning module and an adaptive denoising strategy, both favoring highly-confident samples. Experimental results on three public datasets demonstrate its consistent capability of improving three state-of-the-art social recommendation models by robustly removing 10-40% of original relations. We release the source code at https://github.com/tsinghua-fib-lab/Graph-Denoising-SocialRec.

Crowd stampede disasters often occur, such as recent ones in Indonesia and South Korea, and crowd simulation is particularly important to prevent and avoid such disasters. Most traditional models for crowd simulation, such as the social force model, are hand-designed formulas, which use Newtonian forces to model the interactions between pedestrians. However, such formula-based methods may not be flexible enough to capture the complex interaction patterns in diverse crowd scenarios. Recently, due to the development of the Internet, a large amount of pedestrian movement data has been collected, allowing us to study crowd simulation in a data-driven way. Inspired by the recent success of graph network-based simulation (GNS), we propose a novel method under the framework of GNS, which simulates the crowd in a data-driven way. Specifically, we propose to model the interactions among people and the environment using a heterogeneous graph. Then, we design a heterogeneous gated message-passing network to learn the interaction pattern that depends on the visual field. Finally, the randomness is introduced by modeling the context’s different influences on pedestrians with a probabilistic emission function. Extensive experiments on synthetic data, controlled-environment data and real-world data are performed. Extensive results show that our model can generally capture the three main factors which contribute to crowd trajectories while adapting to the data characteristics beyond the strong assumption of formulas-based methods. As a result, the proposed method outperforms existing methods by a large margin.

Dynamic link prediction is essential for a wide range of domains, including social networks, bioinformatics, knowledge bases, and recommender systems. Existing works have demonstrated that structural information and temporal information are two of the most important information for this problem. However, existing works either focus on modeling them independently or modeling the temporal dynamics of a single structural scale, neglecting the complex correlations among them. This paper proposes to model the inherent correlations among the evolving dynamics of different structural scales for dynamic link prediction. Following this idea, we propose an Attentional Multi-scale Co-evolving Network (AMCNet). Specifically, We model multi-scale structural information by a motif-based graph neural network with multi-scale pooling. Then, we design a hierarchical attention-based sequence-to-sequence model for learning the complex correlations among the evolution dynamics of different structural scales. Extensive experiments on four real-world datasets with different characteristics demonstrate that AMCNet significantly outperforms the state-of-the-art in both single-step and multi-step dynamic link prediction tasks.

Socioeconomic indicators reflect location status from various aspects such as demographics, economy, crime and land usage, which play an important role in the understanding of location-based social networks (LBSNs). Especially, several existing works leverage multi-source data for socioeconomic indicator prediction in LBSNs, which however fail to capture semantic information as well as distil comprehensive knowledge therein. On the other hand, knowledge graph (KG), which distils semantic knowledge from multi-source data, has been popular in recent LBSN research, which inspires us to introduce KG for socioeconomic indicator prediction in LBSNs. Specifically, we first construct a location-based KG (LBKG) to integrate various kinds of knowledge from heterogeneous LBSN data, including locations and other related elements like point of interests (POIs), business areas as well as various relationships between them, such as spatial proximity and functional similarity. Then we propose a hierarchical KG learning model to capture both global knowledge from LBKG and domain knowledge from several sub-KGs. Extensive experiments on three datasets demonstrate our model’s superiority over state-of-the-art methods in socioeconomic indicators prediction. Our code is released at: https://github.com/tsinghua-fib-lab/KG-socioeconomic-indicator-prediction.

As the rapid-spreading disease COVID-19 occupies the world, most governments adopt strict control policies to alleviate the impact of the virus. These policies successfully reduced the prevalence and delayed the epidemic peak, while they are also associated with high economic and social costs. To bridge the microscopic epidemic transmission patterns and control policies, simulation systems play an important role. In this work, we propose an agent-based disease simulator for indoor public spaces, which contribute to most of the transmission in cities. As an example, we study Guangzhou Baiyun International Airport, which is one of the most bustling aviation hubs in China. Specifically, we design a high-efficiency mobility generation module to reconstruct the individual trajectories considering both lingering behavior and crowd mobility, which greatly enhances the credibility of the simulated mobility and ensures real-time performance. Based on the individual trajectories, we propose a multi-path disease transmission module optimized for indoor public spaces, which includes three main transmission paths as close contact transmission, aerosol transmission, and object surface transmission. We design a novel convolution-based algorithm to mimic the diffusion process, which can leverage the high concurrent capability of the graphics processing unit to accelerate the simulation process. Leveraging our simulation paradigm, the effectiveness of common policy interventions can be quantitatively evaluated. For mobility interventions, we find that lingering control is the most effective mobility intervention with 32.35% fewer infections, while increasing social distance and increasing walking speed have a similar effect with 15.15% and 18.02% fewer infections. It demonstrates the importance of introducing crowd mobility into disease transmission simulation. For transmission processes, we find the aerosol transmission involves in 99.99% of transmission, which highlights the importance of ventilation in indoor public spaces. Our simulation also demonstrates that without strict entrance detection to identify the input infections, only performing frequent disinfection cannot achieve desirable epidemic outcomes. Based on our simulation paradigm, we can shed light on better policy designs that achieve a good balance between disease spreading control and social costs.

With the advent of the COVID-19 pandemic, the shortage in medical resources became increasingly more evident. Therefore, efficient strategies for medical resource allocation are urgently needed. However, conventional rule-based methods employed by public health experts have limited capability in dealing with the complex and dynamic pandemic-spreading situation. In addition, model-based optimization methods such as dynamic programming (DP) fail to work since we cannot obtain a precise model in real-world situations most of the time. Model-free reinforcement learning (RL) is a powerful tool for decision-making; however, three key challenges exist in solving this problem via RL: (1) complex situations and countless choices for decision-making in the real world; (2) imperfect information due to the latency of pandemic spreading; and (3) limitations on conducting experiments in the real world since we cannot set up pandemic outbreaks arbitrarily. In this article, we propose a hierarchical RL framework with several specially designed components. We design a decomposed action space with a corresponding training algorithm to deal with the countless choices, ensuring efficient and real-time strategies. We design a recurrent neural network–based framework to utilize the imperfect information obtained from the environment. We also design a multi-agent voting method, which modifies the decision-making process considering the randomness during model training and, thus, improves the performance. We build a pandemic-spreading simulator based on real-world data, serving as the experimental platform. We then conduct extensive experiments. The results show that our method outperforms all baselines, which reduces infections and deaths by 14.25% on average without the multi-agent voting method and up to 15.44% with it.

Travel time estimation (TTE) is a crucial task in intelligent transportation systems, which has been widely used in navigation and route planning. In recent years, several deep learning frameworks have been proposed to capture the dynamic features of road segments or intersections for travel time estimation. However, most existing works do not consider the joint features of the intersections and road segments. Moreover, most deep neural networks for TTE are designed based on empirical knowledge. Since the independent and joint features of intersections and road segments commonly vary with different datasets, the empirical deterministic neural architectures have limited adaptability to different scenarios. To tackle the above problems, we propose a novel automated deep learning framework, namely Automated Spatio-Temporal Dual Graph Convolutional Networks (Auto-STDGCN), for travel time estimation. Specifically, we propose to construct the node-wise graph and edge-wise graph to characterize the spatio-temporal features of intersections and road segments, respectively. In order to capture the joint spatio-temporal correlations of the dual graphs, a hierarchical neural architecture search approach is introduced, whose search space is composed of internal and external search space. In the internal search space, spatial graph convolution and temporal convolution operations are adopted to capture the respective spatio-temporal correlations of the dual graphs. Further, we design the external search space including the node-wise and edge-wise graph convolution operations from the internal architecture search to capture the interaction patterns between the intersections and road segments. We evaluate our proposed model Auto-STDGCN on three real-world datasets, which demonstrates that our model is significantly superior to the state-of-the-art methods. In addition, we also conduct case studies to visualize and explain the neural architectures learned by our model.

Mobile apps have become an indispensable part of people’s daily lives. Users determine what apps to use and when and where to use them based on their tastes, interests, and personal demands, depending on their personality traits. This article aims to infer user profiles from their spatiotemporal mobile app usage behavior. Specifically, we first transform mobile app usage records into a heterogeneous graph. On the graph, nodes represent users, apps, locations, and time slots. Edges describe the co-occurrence of entities in usage records. We then develop a multi-relational heterogeneous graph attention network (MRel-HGAN), an end-to-end system for user profiling. MRel-HGAN first adopts a neighbor sampling strategy based on bootstrapping to sample heavily connected neighbors of a fixed size for each node. Next, we design a relational graph convolutional operation and a multi-relational attention operation. Through such modules, MRel-HGAN can generate node embedding by sufficiently leveraging the rich semantic information of the multi-relational structure in the mobile app usage graph. Experimental results on real-world mobile app usage datasets show the effectiveness and superiority of our MRel-HGAN in the user profiling task for attributes of gender and age.

Satellite imagery depicts the Earth’s surface remotely and provides comprehensive information for many applications, such as land use monitoring and urban planning. Existing studies on unsupervised representation learning for satellite images only take into account the images’ geographic information, ignoring human activity factors. To bridge this gap, we propose using the Point-of-Interest (POI) data to capture human factors and designing a contrastive learning-based framework to consolidate the representation of satellite imagery with POI information. Besides, we introduce a season-invariant representation learning model on satellite imagery, considering that human factors are mostly unchanging with respect to seasons. An attention model is designed at last to merge the representations from the geographic, seasonal, and POI perspectives adaptively. On the basis of real-world datasets collected from Beijing, 1 we evaluate our method for predicting socioeconomic indicators. The results show that the representation containing POI information outperforms the geographic representation in estimating commercial activity-related indicators. Our proposed attentional framework can estimate the socioeconomic indicators with R 2 of 0.874 and outperforms the baseline methods. Furthermore, we explore the differences in the representations of satellite images with varying socioeconomic statuses. Finally, we investigate the impact of geographic and POI perspective information in the representation learning process, as well as the effect of satellite imagery on various spatial resolutions.

Every day, our living city produces a tremendous amount of spatial-temporal data, involved with multiple sources from the individual scale to the city scale. Undoubtedly, such massive urban data can be explored for a better city and better life, as what the urban computing community has been dedicating in recent years. Nevertheless, existing studies are still facing the challenges of data fusion for the urban data as well as the knowledge distillation for specific applications. Moreover, there is a lack of full-featured and user-friendly platforms for both researchers and developers in the urban computing scenario. Therefore, in this article, we present UrbanKG, an urban knowledge graph system to incorporate a knowledge graph with urban computing. Specifically, the system introduces a complete scheme to construct a knowledge graph for urban data fusion. Built upon the data layer, the system further develops the multiple layers of construction, storage, algorithm, operation, and applications, which achieve knowledge distillation and support various functions to the users. We perform representative use cases and demonstrate the system capability of boosting performance in various downstream applications, indicating a promising research direction for knowledge-driven urban computing.

Individual trajectory generation plays an important role in simulation tasks, reconstructing fine-grained mobility behaviors that can be used to evaluate epidemic risks, congestion risks, or commercial profit. Previous research works adopt the Newton’s mechanic-based particle model as their core algorithm, such as the Social Force model. However, real-world human mobility behaviors hardly follow the particle models, especially in the interior scenes where interactions between pedestrians and environments matter. In this article, we propose a Social Force-based trajectory simulator for interior scenarios that improve both trajectory quality and generation speed for interior scenarios. First, we introduce prior scene knowledge to guide the generation process, where pedestrians are armed with exploration behaviors that follow the group-level distribution. It provides more flexibility to simulate complicated human behaviors rather than straight-line movements, generating high-quality individual trajectories. Experiments show that the correlation between the aggregated population distribution of generated trajectories and ground-truth distribution is improved by 11.84% by our method. Second, we optimize the algorithm procedure by introducing a caching mechanism for tenderized intermediate values, along with graph-processing-unit-based implementation. Compared with the baseline Social Force model, we reduced the time consumption by 95%. More importantly, based on our simulation paradigm, we quantitatively evaluate several common mobility interventions in our simulation scenario, which can shed light on better policy designs in public spaces.

Traffic congestion incurs long delay in travel time, which seriously affects our daily travel experiences. Exploring why traffic congestion occurs is significantly important to effectively address the problem of traffic congestion and improve user experience. Traditional approaches to mine the congestion causes depend on human efforts, which is time consuming and cost-intensive. Hence, we aim at discovering the known and unknown causes of traffic congestion in a systematic way. However, to achieve it, there are three challenges: (1) traffic congestion is affected by several factors with complex spatio-temporal relations; (2) there are a few samples of congestion data with known causes due to the limitation of human label; (3) more unknown congestion causes are unexplored since several factors contribute to traffic congestion. To address above challenges, we design a congestion cause discovery system consisting of two modules: (1) congestion feature extraction module, which extracts the important features distinguishing between different causes of congestion; and (2) congestion cause discovery module, which designs a deep semi-supervised learning based framework to discover the causes of traffic congestion with limited labeled data. Specifically, in pre-training stage, it first leverages a few labeled data as prior knowledge to pre-train the model. Then, in clustering stage, we propose two different clustering methods to discover the congestion causes. For the first clustering method, we extend the classic deep embedded clustering model to produce clusters via soft assignment. For the second one, we iteratively usek-means to group the latent features extracted from the pre-trained model, and use the cluster results as pseudo-labels to fine-tune the network. Extensive experiments show that the performance of our methods is superior to the state-of-the-art baselines, which demonstrates the effectiveness of the proposed cause discovery system. Additionally, our system is deployed and used in the practical production environment at Amap.

Street view data is one of the most common data sources for urban prediction tasks, such as estimating socioeconomic status, sensing physical urban changes, and identifying urban villages. Typical research in this field consists of two steps: acquiring a dataset with a street view image sampling algorithm and designing a prediction algorithm for urban prediction tasks. However, most of the previous research focuses on the prediction algorithms, leaving the sampling algorithms underexplored. To fill this gap, we set out to investigate how different street view image sampling algorithms affect the performance of the follow-up tasks and develop an effective street view image sampling algorithm for urban prediction. Through a comprehensive analysis of the performance of different sampling algorithms in three of the most common urban prediction tasks, including commercial activeness prediction, urban liveliness prediction, and urban population prediction, we provide solid empirical evidence that the sampling algorithm significantly affects the performance of the prediction model. Specifically, the performance differences of different sampling algorithms can reach over 25%. Further, we revealed that the sampling step size and the sampling quality are two important factors that affect the performance of a sampling algorithm, while the sampling angle has little influence. Inspired by our analysis results, we propose an effective street view image sampling algorithm, DAS, which contains a denoising module and an adaptive sampling module. It can dynamically adjust the sampling step size to adapt to the optimal size for each region and get rid of the impact of noise images in the meantime. Experiments on three large-scale datasets demonstrate its superior performance over multiple state-of-the-art baselines, and further ablation study shows the effectiveness of each module. Finally, through a thorough discussion of our findings and experimental results, we provide insights into the street view image sampling algorithm design, and we call for more researches in this blank area.

Federated optimization (FedOpt), which targets at collaboratively training a learning model across a large number of distributed clients, is vital for federated learning. The primary concerns in FedOpt can be attributed to the model divergence and communication efficiency, which significantly affect the performance. In this article, we propose a new method, i.e., LoSAC, to learn from heterogeneous distributed data more efficiently. Its key algorithmic insight is to locally update the estimate for the global full gradient after each regular local model update. Thus, LoSAC can keep clients’ information refreshed in a more compact way. In particular, we have studied the convergence result for LoSAC. Besides, the bonus of LoSAC is the ability to defend the information leakage from the recent technique Deep Leakage Gradients (DLG). Finally, experiments have verified the superiority of LoSAC comparing with state-of-the-art FedOpt algorithms. Specifically, LoSAC significantly improves communication efficiency by more than 100% on average, mitigates the model divergence problem, and equips with the defense ability against DLG.

In real-world express systems, couriers need to satisfy not only the delivery demands but also the pick-up demands of customers. Delivery and pickup tasks are usually mixed together within integrated routing plans. Such a mixed routing problem can be abstracted and formulated as Vehicle Routing Problem with Mixed Delivery and Pickup (VRPMDP), which is an NP-hard combinatorial optimization problem. To solve VRPMDP, there are three major challenges as below. (a) Even though successive pickup and delivery tasks are independent to accomplish, the inter-influence between choosing pickup task or delivery task to deal with still exists. (b) Due to the two-way flow of goods between the depot and customers, the loading rate of vehicles leaving the depot affects routing decisions. (c) The proportion of deliveries and pickups will change due to the complex demand situation in real-world scenarios, which requires robustness of the algorithm. To solve the challenges above, we design an encoder-decoder based framework to generate high-quality and robust VRPMDP solutions. First, we consider a VRPMDP instance as a graph and utilize a GNN encoder to extract the feature of the instance effectively. The detailed routing solutions are further decoded as a sequence by the decoder with attention mechanism. Second, we propose a Coordinated Decision of Loading and Routing (CDLR) mechanism to determine the loading rate dynamically after the vehicle returns to the depot, thus avoiding the influence of improper loading rate settings. Finally, the model equipped with a GNN encoder and CDLR simultaneously can adapt to the changes in the proportion of deliveries and pickups. We conduct the experiments to demonstrate the effectiveness of our model. The experiments show that our method achieves desirable results and generalization ability.

The recent outbreak of COVID-19 poses a serious threat to people’s lives. Epidemic control strategies have also caused damage to the economy by cutting off humans’ daily commute. In this article, we develop an Individual-based Reinforcement Learning Epidemic Control Agent (IDRLECA) to search for smart epidemic control strategies that can simultaneously minimize infections and the cost of mobility intervention. IDRLECA first hires an infection probability model to calculate the current infection probability of each individual. Then, the infection probabilities together with individuals’ health status and movement information are fed to a novel GNN to estimate the spread of the virus through human contacts. The estimated risks are used to further support an RL agent to select individual-level epidemic-control actions. The training of IDRLECA is guided by a specially designed reward function considering both the cost of mobility intervention and the effectiveness of epidemic control. Moreover, we design a constraint for control-action selection that eases its difficulty and further improve exploring efficiency. Extensive experimental results demonstrate that IDRLECA can suppress infections at a very low level and retain more than 95% of human mobility.

Traffic prediction is the cornerstone of intelligent transportation system. Accurate traffic forecasting is essential for the applications of smart cities, i.e., intelligent traffic management and urban planning. Although various methods are proposed for spatio-temporal modeling, they ignore the dynamic characteristics of correlations among locations on road network. Meanwhile, most Recurrent Neural Network based works are not efficient enough due to their recurrent operations. Additionally, there is a severe lack of fair comparison among different methods on the same datasets. To address the above challenges, in this article, we propose a novel traffic prediction framework, named Dynamic Graph Convolutional Recurrent Network (DGCRN). In DGCRN, hyper-networks are designed to leverage and extract dynamic characteristics from node attributes, while the parameters of dynamic filters are generated at each time step. We filter the node embeddings and then use them to generate dynamic graph, which is integrated with pre-defined static graph. As far as we know, we are first to employ a generation method to model fine topology of dynamic graph at each time step. Furthermore, to enhance efficiency and performance, we employ a training strategy for DGCRN by restricting the iteration number of decoder during forward and backward propagation. Finally, a reproducible standardized benchmark and a brand new representative traffic dataset are opened for fair comparison and further research. Extensive experiments on three datasets demonstrate that our model outperforms 15 baselines consistently. Source codes are available at https://github.com/tsinghua-fib-lab/Traffic-Benchmark .

Bundle recommendation aims to recommend a bundle of items for a user to consume as a whole. Related work can be divided into two categories: 1) to recommend the platforms prebuilt bundles to users; 2) generate personalized bundles for users. These two problems are not well solved. In this work, we propose two graph neural network models, a BGCN model for prebuilt bundle recommendation, and a BGGN model for personalized bundle generation. First, BGCN unifies the user-item interaction, the user-bundle interaction and the bundle-item affiliation into a heterogeneous graph. With item nodes as the bridge, graph convolutional propagation between user and bundle nodes makes the learned representations capture the item-level semantics. Second, BGGN re-constructs bundles into graphs based on the item co-occurrence pattern and the users supervision signal. The complex and high-order item-item relationships in the bundle graph are explicitly modeled through graph generation. Empirical results demonstrate the substantial performance gains of BGCN and BGGN. We have released the datasets and codes at this link: https://github.com/cjx0525/BGCN.

With the increasing diversity of mobile apps, users install many apps in their smartphones and often use several apps together to meet a specific requirement. Because of the evolution of user habits and app functions, the set of apps using at the same time, i.e., app usage context, may change over time, which represents the dynamic correlation of different apps and even the evolution trend of the whole app ecosystem. Therefore, understanding how an apps usage context changes over time is very meaningful. In this paper, based on a seven-year app usage dataset, we explore the long-term app usage context dynamics and understand the underlying reasons and influence factors behind. Specifically, we build app co-occurrence graphs in different periods and learn app embeddings accordingly by leveraging graph embedding algorithm. We then measure the change of app usage context by the distance between neighboring app embeddings. As for the whole app ecosystem, we find that the change rate of app usage context undergoes up and down phrases, and varies in different app-categories. Furthermore, we explore three influence factors correlated with such dynamics. These results will be helpful for stakeholders to better understand the evolution of mobile users app usage behavior.

Social e-commerce uses social media as a new prevalent platform for online shopping. In this paper, we address the problem of cross-platform recommendation for social e-commerce, i.e., recommending products to users when they are shopping through social media. To the best of our knowledge, this is a new and important problem for all e-commerce companies (e.g. Amazon, Alibaba), but has never been studied before. Existing cross-platform and social related recommendation methods cannot be applied directly to this problem since they do not co-consider the social information and the cross-platform characteristics together. To study this problem, we collect two real-world datasets from social e-commerce services. We first investigate the heterogeneous shopping behaviors between traditional e-commerce app and social media. Based on these observations from data, we propose CROSS (Cross-platform Recommendation for Online Shopping in Social Media), a recommendation framework utilizing not only user-item interaction data on both platforms, but also social relation data on social media. The framework is general and we propose two variants, CROSS-MF and CROSS-NCF. Extensive experiments on two real-world social e-commerce datasets demonstrate that our proposed CROSS significantly outperforms existing state-of-the-art methods.

Origin-Destination (OD) flow contains the information of direction and volume of population mobility between different regions in a city, having significant value in public transportation resource allocation. In this paper, we explore population distribution to infer OD flows, which is called pop2flow (population distribution to OD flows) problem. Compared to the conventional OD forecasting problem by using the historical OD matrix, pop2flow is more challenging because the population distribution carries much less information. In order to solve the pop2flow problem, we proposed a model, Graph-based Spatial-temporal Embedding with Dynamic Fusion (GSTE-DF). Specifically, GSTE-DF is composed of two parts: node embedding learning and flow prediction. The node embedding learning part captures the dynamic spatial-temporal features of population distribution into each nodes embedding. The flow prediction part adopts the learned embeddings and POI (points of interesting) distribution of every two regions to infer the population interaction between them. By conducting extensive experiments on real-world datasets collected in Beijing and New York City, we demonstrate the superiority of GSTE-DF compared to state-of-the-art baselines

In recent years, due to the prevalence of online textual advertisements, increasing businesses recognize their huge potential in product promotion. The high-quality textual content has been empirically shown to have a substantial impact on consumers’ attitudes and decisions. As a result, persuasive tactics play an essential role in online textual advertisements, which are employed to increase the attractiveness, and sequentially increase the conversion rate and sales volume. As the context of persuasion, product attributes, e.g., category and price, also greatly influence the persuasion outcomes. However, they are largely overlooked by existing works. In this paper, we propose a novel framework to study context-aware persuasion by designing a multi-task learning model and performing extensive causal analysis. First, the prediction model recognizes the persuasive tactics employed in an advertising text and predicts their promotion effectiveness. Specifically, we design a disentangled representation learning algorithm to capture the persuasive tactics, and then develop a novel context-aware attention module to model the relationships between persuasive tactics and product attributes. Experiments on a large-scale real-world dataset demonstrate the superior performance of our proposed model over state-of-the-art baselines. Then we show its great practical value by conducting an in-depth causal analysis of context-aware results that our model learns, which offers insightful interpretations and guidelines for marketers to employ persuasive tactics in textual advertisements.

In this work, we aim at developing an effective method to predict user purchase intention with the focus on the price factor in recommender systems. The main difficulties are two-fold: 1) the preference and sensitivity of a user on item price are unknown, which are only implicitly reflected in the items that the user has purchased, and 2) how the item price affects a users intention depends largely on the product category, that is, the perception and affordability of a user on item price could vary significantly across categories. Towards the first difficulty, we propose to model the transitive relationship between user-to-item and item-to-price, taking the inspiration from the recently developed Graph Convolution Networks (GCN). The key idea is to propagate the influence of price on users with items as the bridge, so as to make the learned user representations be price-aware. For the second difficulty, we further integrate item categories into the propagation progress and model the possible pairwise interactions for predicting user-item interactions. We conduct extensive experiments on two real-world datasets, demonstrating the effectiveness of our GCN-based method in learning the price-aware preference of users.

The prevalence of smartphones has promoted the popularity of mobile apps in recent years. Although significant effort has been made to understand mobile app usage, existing studies are based primarily on short-term datasets with a limited time span, e.g., a few months. Therefore, many basic facts about the long-term evolution of mobile app usage are unknown. In this paper, we study how mobile app usage evolves over a long-term period. We first introduce an app usage collection platform named carat, from which we have gathered app usage records of 1,465 users from 2012 to 2017. We then conduct the first study on the long-term evolution processes on a macro-level, i.e., app-category, and micro-level, i.e., individual app. We discover that, on both levels, there is a growth stage enabled by the introduction of new technologies. Then there is a plateau stage caused by high correlations between app categories and a Pareto effect in individual app usage, respectively. Additionally, the evolution of individual app usage undergoes an elimination stage due to fierce intra-category competition. The inter-diversity of app-category and individual app usage exhibits opposing trends: app-category usage assimilates while individual app usage diversifies. Nevertheless, the intra-diversity of both app-category and app usage declines over time. Also, we demonstrate the country barriers of app category usage. We further investigate how different demographics affect the evolutionary processes of app usage. Our study provides useful implications for app developers, market intermediaries, and service providers.

Recommender system is one of the most important information services on today’s Internet. Recently, graph neural networks have become the new state-of-the-art approach to recommender systems. In this survey, we conduct a comprehensive review of the literature on graph neural network-based recommender systems. We first introduce the background and the history of the development of both recommender systems and graph neural networks. For recommender systems, in general, there are four aspects for categorizing existing works: stage, scenario, objective, and application. For graph neural networks, the existing methods consist of two categories: spectral models and spatial ones. We then discuss the motivation of applying graph neural networks into recommender systems, mainly consisting of the high-order connectivity, the structural property of data and the enhanced supervision signal. We then systematically analyze the challenges in graph construction, embedding propagation/aggregation, model optimization, and computation efficiency. Afterward and primarily, we provide a comprehensive overview of a multitude of existing works of graph neural network-based recommender systems, following the taxonomy above. Finally, we raise discussions on the open problems and promising future directions in this area. We summarize the representative papers along with their code repositories in https://github.com/tsinghua-fib-lab/GNN-Recommender-Systems .

Abstract Deep reinforcement learning (DRL) has shown promising results in modeling dynamic user preferences in RS in recent literature. However, training a DRL agent in the sparse RS environment poses a significant challenge. This is because the agent must balance between exploring informative user-item interaction trajectories and using existing trajectories for policy learning, a known exploration and exploitation trade-off. This trade-off greatly affects the recommendation performance when the environment is sparse. In DRL-based RS, balancing exploration and exploitation is even more challenging as the agent needs to deeply explore informative trajectories and efficiently exploit them in the context of RS. To address this issue, we propose a novel intrinsically motivated reinforcement learning (IMRL) method that enhances the agent’s capability to explore informative interaction trajectories in the sparse environment. We further enrich these trajectories via an adaptive counterfactual augmentation strategy with a customised threshold to improve their efficiency in exploitation. Our approach is evaluated on six offline datasets and three online simulation platforms, demonstrating its superiority over existing state-of-the-art methods. The extensive experiments show that our IMRL method outperforms other methods in terms of recommendation performance in the sparse RS environment.

Cooperative Pickup and Delivery Problem (PDP), as a variant of the typical Vehicle Routing Problems (VRP), is an important formulation in many real-world applications, such as on-demand delivery, industrial warehousing, etc. It is of great importance to efficiently provide high-quality solutions of cooperative PDP. However, it is not trivial to provide effective solutions directly due to two major challenges: 1) the structural dependency between pickup and delivery pairs require explicit modeling and representation. 2) the cooperation between different vehicles is highly related to the solution exploration and difficult to model. In this paper, we propose a novel multi-agent reinforcement learning based framework to solve the cooperative PDP (MAPDP). First, we design a paired context embedding to well measure the dependency of different nodes considering their structural limits. Second, we utilize cooperative multi-agent decoders to leverage the decision dependence among different vehicle agents based on a special communication embedding. Third, we design a novel cooperative A2C algorithm to train the integrated model. We conduct extensive experiments on a randomly generated dataset and a real-world dataset. Experiments result shown that the proposed MAPDP outperform all other baselines by at least 1.64\% in all settings, and shows significant computation speed during solution inference.

While hyper-parameters (HPs) are important for knowledge graph (KG) learning, existing methods fail to search them efficiently.To solve this problem, we first analyze the properties of different HPs and measure the transfer ability from small subgraph to the full graph.Based on the analysis, we propose an efficient two-stage search algorithm KG-Tuner, which efficiently explores HP configurations on small subgraph at the first stage and transfers the top-performed configurations for fine-tuning on the large full graph at the second stage.Experiments show that our method can consistently find better HPs than the baseline algorithms within the same time budget, which achieves 9.1% average relative improvement for four embedding models on the large-scale KGs in open graph benchmark.

The disadvantaged population is often underserved and marginalized in technology engagement: prior works show they are generally more reluctant and experience more barriers in adopting and engaging with mainstream technology. Here, we contribute to the HCI4D and ICTD literature through a novel “counter” case study on Chinese social commerce (e.g., Pinduoduo), which 1) first prospers among the traditionally underserved community from developing regions ahead of the more technologically advantaged communities, and 2) has been heavily engaged by this community. Through 12 in-depth interviews with social commerce users from the traditionally underserved community in Chinese developing regions, we demonstrate how social commerce, acting as a “virtual bazaar”, brings online the traditional offline socioeconomic lives the community has lived for ages, fits into the community’s social, cultural, and economic context, and thus effectively promotes technology inclusivity. Our work provides novel insights and implications for building inclusive technology for the “next billion” population.

Understanding economic development and designing government policies requires accurate and timely measurements of socioeconomic activities. In this paper, we show how to leverage city structural information and urban imagery like satellite images and street view images to accurately predict multi-level socioeconomic indicators. Our framework consists of four steps. First, we extract structural information from cities by transforming real-world street networks into city graphs (GeoStruct). Second, we design a contrastive learning-based model to refine urban image features by looking at geographic similarity between images, with images that are geographically close together having similar features (GeoCLR). Third, we propose using street segments as containers to adaptively fuse the features of multi-view urban images, including satellite images and street view images (GeoFuse). Finally, given the city graph with a street segment as a node and a neighborhood area as a subgraph, we jointly model street- and neighborhood-level socioeconomic indicator predictions as node and subgraph classification tasks. The novelty of our method is that we introduce city structure to organize multi-view urban images and model the relationships between socioeconomic indicators at different levels. We evaluate our framework on the basis of real-world datasets collected in multiple cities. Our proposed framework improves performance by over 10% when compared to state-of-the-art baselines in terms of prediction accuracy and recall.

Recently, graph convolutional network (GCN) has become one of the most popular and state-of-the-art collaborative filtering (CF) methods. Existing GCN-based CF studies have made many meaningful and excellent efforts at loss function design and embedding propagation improvement. Despite their successes, we argue that existing methods have not yet properly explored more effective sampling strategy, including both positive sampling and negative sampling. To tackle this limitation, a novel framework named ITSM-GCN is proposed to carry out our designed Informative Training Sample Mining (ITSM) sampling strategy for the learning of GCN-based CF models. Specifically, we first adopt and improve the dynamic negative sampling (DNS) strategy, which achieves considerable improvements in both training efficiency and recommendation performance. More importantly, we design two potentially positive training sample mining strategies, namely a similarity-based sampler and score-based sampler, to further enhance GCN-based CF. Extensive experiments show that ITSM-GCN significantly outperforms state-of-the-art GCN-based CF models, including LightGCN, SGL-ED and SimpleX. For example, ITSM-GCN improves on SimpleX by 12.0%, 3.0%, and 1.2% on [email protected] for Amazon-Books, Yelp2018 and Gowalla, respectively.

Session-based recommendation (SBR) aims to recommend items based on user behaviors in a session. For the online life service platforms, such as Meituan, both the user's location and the current time primarily cause the different patterns and intents in user behaviors. Hence, spatiotemporal context plays a significant role in the recommendation on those platforms, which motivates an important problem of spatiotemporal-aware session-based recommendation (STSBR). Since the spatiotemporal context is introduced, there are two critical challenges: 1) how to capture session-level relations of spatiotemporal context (inter-session view), and 2) how to model the complex user decision-making process at a specific location and time (intra-session view). To address them, we propose a novel solution named STAGE in this paper. Specifically, STAGE first constructs a global information graph to model the multi-level relations among all sessions, and a session decision graph to capture the complex user decision process for each session. STAGE then performs inter-session and intra-session embedding propagation on the constructed graphs with the proposed graph attentive convolution (GAC) to learn representations from the above two perspectives. Finally, the learned representations are combined with spatiotemporal-aware soft-attention for final recommendation. Extensive experiments on two datasets from Meituan demonstrate the superiority of STAGE over state-of-the-art methods. Further studies also verify that each component is effective.

In recent years, short-form video platforms have emerged rapidly and attracted a large and wide variety of users, with the help of advanced recommendation algorithms. Despite the great success, the algorithms have caused some negative effects, such as information cocoon, algorithm unfairness,etc. In this work, we focus on theinformation cocoon that measures overwhelmingly homogeneity of users' video consumption. Specifically, we conduct an exploratory study of this phenomenon on a top short-form video platform, with one-year behavioral records of new users. First, we evaluate the evolution of users' information cocoons and find the limitation of the diversity of video content that users consume. In addition, we further explore user cocoons via the correlation analysis from three aspects, including user demographics, video content, and user-recommender interactions driven by algorithms and user preferences. Correspondingly, we observe that video content plays a more significant role in affecting user cocoons than demographics does. In terms of user-recommender interactions, more accurate personalization does not contribute to more severe information cocoons necessarily, while users with narrow preferences are more likely to be trapped. In summary, our study illuminates the current concern of information cocoons that may hurt user experience on short-form video platforms, and offers potential directions for mitigation implied by the correlation analysis.

Traffic prediction plays an important role in many intelligent transportation systems. Many existing works design static neural network architecture to capture complex spatio-temporal correlations, which is hard to adapt to different datasets. Although recent neural architecture search approaches have addressed this problem, it still adopts a coarse-grained search with pre-defined and fixed components in the search space for spatio-temporal modeling. In this paper, we propose a novel neural architecture search framework, entitled AutoSTS, for automated spatio-temporal synchronous modeling in traffic prediction. To be specific, we design a graph neural network (GNN) based architecture search module to capture localized spatio-temporal correlations, where multiple graphs built from different perspectives are jointly utilized to find a better message passing way for mining such correlations. Further, we propose a convolutional neural network (CNN) based architecture search module to capture temporal dependencies with various ranges, where gated temporal convolutions with different kernel sizes and convolution types are designed in search space. Extensive experiments on six public datasets demonstrate that our model can achieve 4%-10% improvements compared with other methods.

Predicting future origin-destination (OD) flow is essential for urban planning since it provides feedback for planning adjustment and reference for road planning. However, OD prediction for urban planning scenarios is unique as it typically lacks training data. A common practice is to refer to data from other cities, which causes the out-of-distribution (OOD) problem. A promising solution is to leverage causal information in the data. However, there are two challenges in utilizing causal information in urban planning scenarios: (a) Urban system has numerous factors, and only part of them indicate causal information. (b) The planned city development correlates with original city characteristics, therefore bringing confounding bias to the causal modelling process. In this paper, we propose designs to solve both challenges. Specifically, we first design a causal disentangled representation module to identify causal factors in attributes. Second, we adopt a variational sample re-weighting module to reduce the confounding bias. Our proposed model outperforms seven state-of-the-art baselines on three real-world datasets, achieving an average improvement of 9.59% in the MAE metric. Further in-depth analysis shows our method's robustness across different urban planning scenarios and outstanding performance in predicting extremely large OD flows, which corroborates the contribution of our designs to the urban planning field.

With the gradual improvements in COVID-19 metrics and the accelerated immunization progress, countries around the world have began to focus on reviving the economy while continuously strengthening epidemic control. POInt-of-Interest (POI) reopening, as a necessity for restoring human mobilities, has become a crucial step to recouple economic recovery and public health management. In contrast to the lock-down policy, POI reopening demands a dynamic trade-off between epidemic interventions and economic costs. In the urban scenario, there exist three key challenges in developing effective POI reopening strategies as follows. (1) During the POI reopening process, there are multiple urban factors affecting the epidemic transmission, which are difficult to simultaneously incorporate and balance in a single reopening strategy; (2) the effects of POI reopening on both economic recovery and epidemic control are long-term, which are hard to capture by static models; and (3) the dual objectives of minimizing infections and maintaining POIs' visits are conflicting, making it difficult to achieve a flexible and scalable trade-off. To tackle the above challenges, we propose Reopener, a deep reinforcement learning (RL) framework for smart POI reopening. First, we utilize a bipartite graph neural network to automatically encode all urban factors that would affect the epidemic prevention and POI visit restriction. Second, we employ a RL-based deep policy network to enable flexible updates in restrictions on POIs along with the trend of epidemic. Third, we design a novel reward function to guide the RL agent to learn smartly, thus comprehensively trading off infections and visit sustainability of POIs. Extensive experimental results demonstrate that Reopener outperforms all baseline methods with remarkable improvements, by reducing the overall economic cost by at least 6.42%. Reopener can effectively suppress infections and support a phase-based POI reopening process, which provides valuable insights for strategy design in post-COVID-19 economic recovery.

With the increase of computing power and the development of data science, modeling and simulation are becoming indispensable tools in urban science research. Cities, as complex systems made up of many aspects such as mobility, infrastructure, have complex interactions and relationships among multiple elements. In order to provide researchers with tools to model and simulate complex urban systems, we first propose a city model that focuses on three key concepts: human, thing and space. According to the city model, we design and develop Mirage, an efficient and extensible city simulation framework and also implement an efficient mobility module as Mirage's necessary module. To show the extensibility of Mirage, we build application cases about urban vulnerability and decision making. We also conduct extensive experiments to verify the efficiency of Mirage and its mobility module.

To control the outbreak of COVID-19, efficient individual mobility intervention for EPidemic Control (EPC) strategies are of great importance, which cut off the contact among people at epidemic risks and reduce infections by intervening the mobility of individuals. Reinforcement Learning (RL) is powerful for decision making, however, there are two major challenges in developing an RL-based EPC strategy: (1) the unobservable information about asymptomatic infections in the incubation period makes it difficult for RL's decision-making, and (2) the delayed rewards for RL causes the deficiency of RL learning. Since the results of EPC are reflected in both daily infections (including unobservable asymptomatic infections) and long-term cumulative cases of COVID-19, it is quite daunting to design an RL model for precise mobility intervention. In this paper, we propose a Variational hiErarcHICal reinforcement Learning method for Epidemic control via individual-level mobility intervention, namely Vehicle. To tackle the above challenges, Vehicle first exploits an information rebuilding module that consists of a contact-risk bipartite graph neural network and a variational LSTM to restore the unobservable information. The contact-risk bipartite graph neural network estimates the possibility of an individual being an asymptomatic infection and the risk of this individual spreading the epidemic, as the current state of RL. Then, the Variational LSTM further encodes the state sequence to model the latency of epidemic spreading caused by unobservable asymptomatic infections. Finally, a Hierarchical Reinforcement Learning framework is employed to train Vehicle, which contains dual-level agents to solve the delayed reward problem. Extensive experimental results demonstrate that Vehicle can effectively control the spread of the epidemic. Vehicle outperforms the state-of-the-art baseline methods with remarkably high-precision mobility interventions on both symptomatic and asymptomatic infections.

In the fight against the COVID-19 pandemic, vaccines are the most critical resource but are still in short supply around the world. Therefore, efficient vaccine allocation strategies are urgently called for, especially in large-scale metropolis where uneven health risk is manifested in nearby neighborhoods. However, there exist several key challenges in solving this problem: (1) great complexity in the large scale scenario adds to the difficulty in experts' vaccine allocation decision making; (2) heterogeneous information from all aspects in the metropolis' contact network makes information utilization difficult in decision making; (3) when utilizing the strong decision-making ability of reinforcement learning (RL) to solve the problem, poor explainability limits the credibility of the RL strategies. In this paper, we propose a reinforcement learning enhanced experts method. We deal with the great complexity via a specially designed algorithm aggregating blocks in the metropolis into communities and we hierarchically integrate RL among the communities and experts solution within each community. We design a self-supervised contact network representation algorithm to fuse the heterogeneous information for efficient vaccine allocation decision making. We conduct extensive experiments in three metropolis with real-world data and prove that our method outperforms the best baseline, reducing 9.01% infections and 12.27% deaths.We further demonstrate the explainability of the RL model, adding to its credibility and also enlightening the experts in turn.

Consumption intent, defined as the decision-driven force of consumption behaviors, is crucial for improving the explainability and performance of user-modeling systems, with various downstream applications like recommendation and targeted marketing. However, consumption intent is implicit, and only a few known intents have been explored from the user consumption data in Meituan. Hence, discovering new consumption intents is a crucial but challenging task, which suffers from two critical challenges: 1) how to encode the consumption intent related to multiple aspects of preferences, and 2) how to discover the new intents with only a few known ones. In Meituan, we designed the AutoIntent system, consisting of the disentangled intent encoder and intent discovery decoder, to address the above challenges. Specifically, for the disentangled intent encoder, we construct three groups of dual hypergraphs to capture the high-order relations under the three aspects of preferences and then utilize the designed hypergraph neural networks to extract disentangled intent features. For the intent discovery decoder, we propose to build intent-pair pseudo labels based on the denoised feature similarities to transfer knowledge from known intents to new ones. Extensive offline evaluations verify that AutoIntent can effectively discover unknown consumption intents. Moreover, we deploy AutoIntent in the recommendation engine of the Meituan APP, and the further online evaluation verifies its effectiveness.

In online information systems, users make decisions based on factors of several specific aspects, such as brand, price, etc. Existing recommendation engines ignore the explicit modeling of these factors, leading to sub-optimal recommendation performance. In this paper, we focus on the real-world scenario where these factors can be explicitly captured (the users are exposed with decision factor-based persuasion texts, i.e., persuasion factors). Although it allows us for explicit modeling of user-decision process, there are critical challenges including the persuasion factor's representation learning and effect estimation, along with the data-sparsity problem. To address them, in this work, we present our POEM (short for Persuasion factOr Effect Modeling) system. We first propose the persuasion-factor graph convolutional layers for encoding and learning representations from the persuasion-aware interaction data. Then we develop a prediction layer that fully considers the user sensitivity to the persuasion factors. Finally, to address the data-sparsity issue, we propose a counterfactual learning-based data augmentation method to enhance the supervision signal. Real-world experiments demonstrate the effectiveness of our proposed framework of modeling the effect of persuasion factors.

Traffic congestion incurs long delay in travel time, which seriously affects our daily travel experiences. Exploring why traffic congestion occurs is significantly important to effectively address the problem of traffic congestion and improve user experience. Traditional approaches to mine the congestion causes depend on human efforts, which is time consuming and cost-intensive. Hence, we aim to discover the known and unknown causes of traffic congestion in a systematic way. However, to achieve it, there are three challenges: 1) traffic congestion is affected by several factors with complex spatio-temporal relations; 2) the amount of congestion data with known causes is small due to the limitation of human label; 3) more unknown congestion causes are unexplored since several factors contribute to traffic congestion. To address above challenges, we design a congestion cause discovery system consisting of two modules: 1) congestion feature extraction, which extracts the important features influencing congestion; and 2) congestion cause discovery, which utilize a deep semi-supervised learning based method to discover the causes of traffic congestion with limited labeled causes. Specifically, it first leverages a few labeled data as prior knowledge to pre-train the model. Then, the k-means algorithm is performed to produce the clusters. Extensive experiments show that the performance of our proposed method is superior to the baselines. Additionally, our system is deployed and used in the practical production environment at Amap.

Large-scale vehicle trajectories bring great benefits in understanding urban mobility, and can be used to promote a wide range of applications in building intelligent transportation systems. Traditional approaches cannot recover the trajectories of all the vehicles on the roads since they are based on partial trajectory data. To address it, we study the all-vehicle trajectory recovery based on traffic camera video data. However, there are two challenges in this study. First, the quality of the images captured by traffic cameras is unbalanced, so it is hard to identify the same vehicles. Second, the traffic camera observation data are sparse due to the incompleteness of the traffic cameras and possible vehicle miss from the traffic cameras. To deal with these challenges, we design a novel system to recover the vehicle trajectory with the granularity of the road intersection. In this system, we propose an iterative framework to jointly optimize the vehicle re-identification and trajectory recovery tasks. In the vehicle re-identification task, we propose an effective strategy to guide the vehicle clustering based on visual features and the spatio-temporal constraint features updated by the trajectory discovery task. In the trajectory recovery task, we model the spatial and temporal relations as well as the vehicle miss problem by a probabilistic approach to recover the trajectories. Extensive experiments demonstrate that our framework outperforms the existing state-of-art solutions. Finally, our system is deployed in practical applications of SenseTime, China, including traffic congestion analysis and traffic signal control.

Human daily activities, such as working, eating out, and traveling, play an essential role in contact tracing and modeling the diffusion patterns of the COVID-19 pandemic. However, individual-level activity data collected from real scenarios are highly limited due to privacy issues and commercial concerns. In this paper, we present a novel framework based on generative adversarial imitation learning, to generate artificial activity trajectories that retain both the fidelity and utility of the real-world data. To tackle the inherent randomness and sparsity of irregular-sampled activities, we innovatively capture the spatiotemporal dynamics underlying trajectories by leveraging neural differential equations. We incorporate the dynamics of continuous flow between consecutive activities and instantaneous updates at observed activity points in temporal evolution and spatial transformation. Extensive experiments on two real-world datasets show that our proposed framework achieves superior performance over state-of-the-art baselines in terms of improving the data fidelity and data utility in facilitating practical applications. Moreover, we apply the synthetic data to model the COVID-19 spreading, and it achieves better performance by reducing the simulation MAPE over the baseline by more than 50%. The source code is available online: https://github.com/tsinghua-fib-lab/Activity-Trajectory-Generation.

Crowd simulation acts as the basic component in traffic management, urban planning, and emergency management. Most existing approaches use physics-based models due to their robustness and strong generalizability, yet they fall short in fidelity since human behaviors are too complex and heterogeneous for a universal physical model to describe. Recent research tries to solve this problem by deep learning methods. However, they are still unable to generalize well beyond training distributions. In this work, we propose to jointly leverage the strength of the physical and neural network models for crowd simulation by a Physics-Infused Machine Learning (PIML) framework. The key idea is to let the two models learn from each other by iteratively going through a physics-informed machine learning process and a machine-learning-aided physics discovery process. We present our realization of the framework with a novel neural network model, Physics-informed Crowd Simulator (PCS), and tailored interaction mechanisms enabling the two models to facilitate each other. Specifically, our designs enable the neural network model to identify generalizable signals from real-world data better and yield physically consistent simulations with the physical model's form and simulation results as a prior. Further, by performing symbolic regression on the well-trained neural network, we obtain improved physical models that better describe crowd dynamics. Extensive experiments on two publicly available large-scale real-world datasets show that, with the framework, we successfully obtain a neural network model with strong generalizability and a new physical model with valid physical meanings at the same time. Both models outperform existing state-of-the-art simulation methods in accuracy, fidelity, and generalizability, which demonstrates the effectiveness of the PIML framework for improving simulation performance and its capability for facilitating scientific discovery and deepening our understandings of crowd dynamics. We release the codes at https://github.com/tsinghua-fib-lab/PIML.

The large-scale vehicle routing problems (VRPs) are defined based on the classical VRPs with thousands of customers. It is an important optimization problem in modern logistic systems, since efficiently obtaining high-quality solutions can greatly reduce operation expenses as well as improve customer satisfaction. Most existing algorithms, including traditional non-learning heuristics and learning-based methods, only perform well on small-scale instances with usually no more than hundreds of customers. In this paper we present a novel Rewriting-by-Generating (RBG) framework which solves large-scale VRPs hierarchically. RBG consists of a rewriter agent that refines the customer division globally and an elementary generator to infer regional solutions locally. It is also flexible with multiple CVRP variant problems and could be continuously evolved with more up-to-date generator designs. We conduct extensive experiments on both synthetic and real-world data to demonstrate the effectiveness and efficiency of our proposed RBG framework. It outperforms HGS, one of the best heuristic method for CVRPs and also shortens the inference time. Online evaluation is also conducted on a deployed express platform in Guangdong, China, where RBG shows advantages to other alternative built-in algorithms.

Recommender systems are prone to be misled by biases in the data. Models trained with biased data fail to capture the real interests of users, thus it is critical to alleviate the impact of bias to achieve unbiased recommendation. In this work, we focus on an essential bias in micro-video recommendation, duration bias. Specifically, existing micro-video recommender systems usually consider watch time as the most critical metric, which measures how long a user watches a video. Since videos with longer duration tend to have longer watch time, there exists a kind of duration bias, making longer videos tend to be recommended more against short videos. In this paper, we empirically show that commonly-used metrics are vulnerable to duration bias, making them NOT suitable for evaluating micro-video recommendation. To address it, we further propose an unbiased evaluation metric, called WTG (short for Watch Time Gain). Empirical results reveal that WTG can alleviate duration bias and better measure recommendation performance. Moreover, we design a simple yet effective model named DVR (short for Debiased Video Recommendation) that can provide unbiased recommendation of micro-videos with varying duration, and learn unbiased user preferences via adversarial learning. Extensive experiments based on two real-world datasets demonstrate that DVR successfully eliminates duration bias and significantly improves recommendation performance with over 30% relative progress. Codes and datasets are released at https://github.com/tsinghua-fib-lab/WTG-DVR.

Session-based recommendation (SBR) aims at the next-item prediction with a short behavior session. Existing solutions fail to address two main challenges: 1) user interests are shown as dynamically coupled intents, and 2) sessions always contain noisy signals. To address them, in this paper, we propose a hypergraph-based solution, HIDE. Specifically, HIDE first constructs a hypergraph for each session to model the possible interest transitions from distinct perspectives. HIDE then disentangles the intents under each item click in micro and macro manners. In the micro-disentanglement, we perform intent-aware embedding propagation on session hypergraph to adaptively activate disentangled intents from noisy data. In the macro-disentanglement, we introduce an auxiliary intent-classification task to encourage the independence of different intents. Finally, we generate the intent-specific representations for the given session to make the final recommendation. Benchmark evaluations demonstrate the significant performance gain of our HIDE over the state-of-the-art methods.

Widely applied in today's recommender systems, sequential recommendation predicts the next interacted item for a given user via his/her historical item sequence. However, sequential recommendation suffers data sparsity issue like most recommenders. To extract auxiliary signals from the data, some recent works exploit self-supervised learning to generate augmented data via dropout strategy, which, however, leads to sparser sequential data and obscure signals. In this paper, we propose D ual C ontrastive N etwork (DCN) to boost sequential recommendation, from a new perspective of integrating auxiliary user-sequence for items. Specifically, we propose two kinds of contrastive learning. The first one is the dual representation contrastive learning that minimizes the distances between embeddings and sequence-representations of users/items. The second one is the dual interest contrastive learning which aims to self-supervise the static interest with the dynamic interest of next item prediction via auxiliary training. We also incorporate the auxiliary task of predicting next user for a given item's historical user sequence, which can capture the trends of items preferred by certain types of users. Experiments on benchmark datasets verify the effectiveness of our proposed method. Further ablation study also illustrates the boosting effect of the proposed components upon different sequential models.

Most modern recommender systems predict users' preferences with two components: user and item embedding learning, followed by the user-item interaction modeling. By utilizing the auxiliary review information accompanied with user ratings, many of the existing review-based recommendation models enriched user/item embedding learning ability with historical reviews or better modeled user-item interactions with the help of available user-item target reviews. Though significant progress has been made, we argue that current solutions for review-based recommendation suffer from two drawbacks. First, as review-based recommendation can be naturally formed as a user-item bipartite graph with edge features from corresponding user-item reviews, how to better exploit this unique graph structure for recommendation? Second, while most current models suffer from limited user behaviors, can we exploit the unique self-supervised signals in the review-aware graph to guide two recommendation components better? To this end, in this paper, we propose a novel Review-aware Graph Contrastive Learning (RGCL) framework for review-based recommendation. Specifically, we first construct a review-aware user-item graph with feature-enhanced edges from reviews, where each edge feature is composed of both the user-item rating and the corresponding review semantics. This graph with feature-enhanced edges can help attentively learn each neighbor node weight for user and item representation learning. After that, we design two additional contrastive learning tasks (i.e., Node Discrimination and Edge Discrimination) to provide self-supervised signals for the two components in recommendation process. Finally, extensive experiments over five benchmark datasets demonstrate the superiority of our proposed RGCL compared to the state-of-the-art baselines.

Recently, graph neural network (GNN) has become the new state-of-the-art approach in many recommendation problems, with its strong ability to handle structured data and to explore high-order information. However, as the recommendation tasks are diverse and various in the real world, it is quite challenging to design proper GNN methods for specific problems. In this tutorial, we focus on the critical challenges of GNN-based recommendation and the potential solutions. Specifically, we start from an extensive background of recommender systems and graph neural networks. Then we fully discuss why GNNs are required in recommender systems and the four parts of challenges, including graph construction, network design, optimization, and computation efficiency. Then, we discuss how to address these challenges by elaborating on the recent advances of GNN-based recommendation models, with a systematic taxonomy from four critical perspectives: stages, scenarios, objectives, and applications. Last, we finalize this tutorial with conclusions and discuss important future directions.

Accurate churn prediction for retaining users is keenly important for online services because it determines their survival and prosperity. Recent research has specified social influence to be one of the most important reasons for user churn, and thereby many works start to model its effects on user churn to improve the prediction performance. However, existing works only use the data's correlational information while neglecting the problem's causal nature. Specifically, the fact that a user's churn is correlated with some social factors does not mean he/she is actually influenced by his/her friends, which results in inaccurate and unexplainable predictions of the existing methods. To bridge this gap, we develop a counterfactual modeling framework for churn prediction, which can effectively capture the causal information of social influence for accurate and explainable churn predictions. Specifically, we first propose a backbone framework that uses two separate embeddings to model users' endogenous churn intentions and the exogenous social influence. Then, we propose a counterfactual data augmentation module to introduce the causal information to the model by providing partially labeled counterfactual data. Finally, we design a three-headed counterfactual prediction framework to guide the model to learn causal information to facilitate churn prediction. Extensive experiments on two large-scale datasets with different types of social relations show our model's superior prediction performance compared with the state-of-the-art baselines. We further conduct an in-depth analysis of the prediction results demonstrating our proposed method's ability to capture causal information of social influence and give explainable churn predictions, which provide insights into designing better user retention strategies.

Network traffic data facilitates understanding the Internet of Things (IoT) behaviors and improving IoT service quality in the real world. However, large-scale IoT traffic data is rarely accessible, and privacy issues also impede realistic data sharing even with anonymous personal identifiable information. Researchers propose to generate synthetic IoT traffic but fail to cover the multiple services provided by widespread real-world IoT devices. In this work, we take the first step to generate large-scale IoT traffic via a knowledge-enhanced generative adversarial network (GAN) framework, which introduces both the semantic knowledge (e.g., location and environment information) and the network structure knowledge for various IoT devices via a knowledge graph. We use a condition mechanism to incorporate the knowledge and device category for IoT traffic generation. Then, we adopt LSTM and a self-attention mechanism to capture the temporal correlation in the traffic series. Extensive experiment results show that the synthetic IoT traffic datasets generated by our proposed model outperform state-of-art baselines in terms of data fidelity and applications. Moreover, our proposed model is able to generate realistic data by only training on small real datasets with knowledge enhanced.

Satellite imagery depicts the earth’s surface remotely and provides comprehensive information for many applications, such as land use monitoring and urban planning. Existing studies on unsupervised representation learning for satellite images only take into account the images’ geographic information, ignoring human activity factors. To bridge this gap, we propose using Point-of-Interest (POI) data to capture human factors and design a contrastive learning-based framework to consolidate the representation of satellite imagery with POI information. Also, we design an attention model that merges the representations from the geographic and POI perspectives adaptively. On the basis of real-world datasets collected from Beijing, we evaluate our method for predicting socioeconomic indicators. The results show that the representation containing POI information outperforms the geographic representation in estimating commercial activity-related indicators. Our proposed framework can estimate the socioeconomic indicators with an R2 of 0.874 and outperforms the baseline methods.

Modeling user’s long-term and short-term interests is crucial for accurate recommendation. However, since there is no manually annotated label for user interests, existing approaches always follow the paradigm of entangling these two aspects, which may lead to inferior recommendation accuracy and interpretability. In this paper, to address it, we propose a Contrastive learning framework to disentangle Long and Short-term interests for Recommendation (CLSR) with self-supervision. Specifically, we first propose two separate encoders to independently capture user interests of different time scales. We then extract long-term and short-term interests proxies from the interaction sequences, which serve as pseudo labels for user interests. Then pairwise contrastive tasks are designed to supervise the similarity between interest representations and their corresponding interest proxies. Finally, since the importance of long-term and short-term interests is dynamically changing, we propose to adaptively aggregate them through an attention-based network for prediction. We conduct experiments on two large-scale real-world datasets for e-commerce and short-video recommendation. Empirical results show that our CLSR consistently outperforms all state-of-the-art models with significant improvements: GAUC is improved by over 0.01, and NDCG is improved by over 4%. Further counterfactual evaluations demonstrate that stronger disentanglement of long and short-term interests is successfully achieved by CLSR. The code and data are available at https://github.com/tsinghua-fib-lab/CLSR.

Internet of Things (IoT) devices are increasingly growing in mobile networks with the ubiquity of various IoT services. They share the same infrastructure with smartphones while having different requirements for communication resources and security defense mechanisms. Distinguishing IoT devices from smartphones has far-reaching implications on effective network design, resource allocation scheme, pricing scheme, etc. In this article, we distinguish between 12 107 IoT devices and 12 693 smartphones in the real world via characterizing their network traffic. The IoT devices fall into five categories, namely, locating, monitoring, portable, point of sale (POS), and vehicle. We analyze the device behaviors from the network domain, physical domain, and time domain, make comparisons between each kind of IoT devices and smartphones, and design effective features based on the distinguishable network behavior characteristics at packet level, traffic level, and mobility level. Then, we train several classifiers based on our feature set to identify different kinds of mobile devices. Specifically, the accuracy of identifying IoT devices from smartphones achieves 95.86%, and the accuracies of distinguishing IoT devices in each category from smartphones are all over 95%. In the trained classifiers, feature importance verifies the discriminability of different network traffic characteristics observed in our multidomain measurement. Our study reveals the network traffic behavior characteristics for IoT devices, and successfully distinguishes them from smartphones, which paves the way for better network design, resource allocation, pricing scheme, and security defense mechanisms.

In recent years, China has witnessed the proliferation and success of the online food delivery industry, an emerging type of the gig economy. Online food deliverers who deliver the food from restaurants to customers play a critical role in enabling this industry. Mediated by algorithms and coupled with interactions with multiple stakeholders, this emerging kind of labor has been taken by millions of people. In this paper, we present a mixed-methods analysis to investigate this labor of online food deliverers and uncover how the mediation of algorithms shapes it. Combining large-scale quantitative data-driven investigations of 100,000 deliverers' behavioral data with in-depth qualitative interviews with 15 online food deliverers, we demonstrate their working activities, identify how algorithms mediate their delivery procedures, and reveal how they perceive their relationships with different stakeholders as a result of their algorithm-mediated labor. Our findings provide important implications for enabling better experiences and more humanized labor of deliverers as well as workers in gig economies of similar kinds.

Recommender systems are playing an increasingly important role in alleviating information overload and supporting users' various needs, e.g., consumption, socialization, and entertainment. However, limited research focuses on how values should be extensively considered in industrial deployments of recommender systems, the ignorance of which can be problematic. To fill this gap, in this paper, we adopt Value Sensitive Design to comprehensively explore how practitioners and users recognize different values of current industrial recommender systems. Based on conceptual and empirical investigations, we focus on five values: recommendation quality, privacy, transparency, fairness, and trustworthiness. We further conduct in-depth qualitative interviews with 20 users and 10 practitioners to delve into their opinions about these values. Our results reveal the existence and sources of tensions between practitioners and users in terms of value interpretation, evaluation, and practice, which provide novel implications for designing more human-centric and value-sensitive recommender systems.

Urban anomalies may result in loss of life or property if not handled properly. Automatically alerting anomalies in their early stage or even predicting anomalies before happening is of great value for populations. Recently, data-driven urban anomaly analysis frameworks have been forming, which utilize urban big data and machine learning algorithms to detect and predict urban anomalies automatically. In this survey, we make a comprehensive review of the state-of-the-art research on urban anomaly analytics. We first give an overview of four main types of urban anomalies, traffic anomaly, unexpected crowds, environment anomaly, and individual anomaly. Next, we summarize various types of urban datasets obtained from diverse devices, i.e., trajectory, trip records, CDRs, urban sensors, event records, environment data, social media and surveillance cameras. Subsequently, a comprehensive survey of issues on detecting and predicting techniques for urban anomalies is presented. Finally, research challenges and open problems as discussed.

No abstract available.

It is essential to predict crowd flow precisely in a city, which is practically partitioned into irregular regions based on road networks and functionality. However, prior works mainly focus on grid-based crowd flow prediction, where a city is divided into many regular grids. Although Convolutional Neural Netwok (CNN) is powerful to capture spatial dependence from grid-based Euclidean data, it fails to tackle non-Euclidean data, which reflect the correlations among irregular regions. Besides, prior works fail to jointly capture the hierarchical spatio-temporal dependence from both regular and irregular regions. Finally, the correlations among regions are time-varying and functionality-related. However, the combination of dynamic and semantic attributes of regions are ignored by related works. To address the above challenges, in this article, we propose a novel model to tackle the flow prediction task for irregular regions. First, we employ CNN and Graph Neural Network (GNN) to capture micro and macro spatial dependence among grid-based regions and irregular regions, respectively. Further, we think highly of the dynamic inter-region correlations and propose a location-aware and time-aware graph attention mechanism named Semantic Graph Attention Network (Semantic-GAT), based on dynamic node attribute embedding and multi-view graph reconstruction. Extensive experimental results based on two real-life datasets demonstrate that our model outperforms 10 baselines by reducing the prediction error around 8%.

introduction Share on Introduction to the Special Issue on Deep Learning for Spatio-Temporal Data: Part 2 Editors: Senzhang Wang Central South University, China Central South University, ChinaView Profile , Junbo Zhang JD Intelligent Cities Research, JD iCity, JD Tech, China JD Intelligent Cities Research, JD iCity, JD Tech, ChinaView Profile , Yanjie Fu University of Central Florida, U.S.A. University of Central Florida, U.S.A.View Profile , Yong Li Tsinghua University, China Tsinghua University, ChinaView Profile Authors Info & Claims ACM Transactions on Intelligent Systems and TechnologyVolume 13Issue 2April 2022 Article No.: 17pp 1–4https://doi.org/10.1145/3510023Online:26 March 2022Publication History 0citation147DownloadsMetricsTotal Citations0Total Downloads147Last 12 Months147Last 6 weeks10 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

No abstract available.

Crowd flow prediction is of great importance in a wide range of applications from urban planning, traffic control to public safety. It aims at predicting the inflow (the traffic of crowds entering a region in a given time interval) and outflow (the traffic of crowds leaving a region for other places) of each region in the city with knowing the historical flow data. In this article, we propose DeepSTN+, a deep learning-based convolutional model, to predict crowd flows in the metropolis. First, DeepSTN+ employs the ConvPlus structure to model the long-range spatial dependence among crowd flows in different regions. Further, PoI distributions and time factor are combined to express the effect of location attributes to introduce prior knowledge of the crowd movements. Finally, we propose a temporal attention-based fusion mechanism to stabilize the training process, which further improves the performance. Extensive experimental results based on four real-life datasets demonstrate the superiority of our model, i.e., DeepSTN+ reduces the error of the crowd flow prediction by approximately 10%–21% compared with the state-of-the-art baselines.

Web systems that provide the same functionality usually share a certain amount of items. This makes it possible to combine data from different websites to improve recommendation quality, known as the cross-domain recommendation task. Despite many research efforts on this task, the main drawback is that they largely assume the data of different systems can be fully shared . Such an assumption is unrealistic different systems are typically operated by different companies, and it may violate business privacy policy to directly share user behavior data since it is highly sensitive. In this work, we consider a more practical scenario to perform cross-domain recommendation. To avoid the leak of user privacy during the data sharing process, we consider sharing only the information of the item side, rather than user behavior data. Specifically, we transfer the item embeddings across domains, making it easier for two companies to reach a consensus (e.g., legal policy) on data sharing since the data to be shared is user-irrelevant and has no explicit semantics. To distill useful signals from transferred item embeddings, we rely on the strong representation power of neural networks and develop a new method named as NATR (short for N eural A ttentive T ransfer R ecommendation ). We perform extensive experiments on two real-world datasets, demonstrating that NATR achieves similar or even better performance than traditional cross-domain recommendation methods that directly share user-relevant data. Further insights are provided on the efficacy of NATR in using the transferred item embeddings to alleviate the data sparsity issue.

The wide adoption of mobile devices has provided us with a massive volume of human mobility records. However, a large portion of these records is unlabeled, i.e., only have GPS coordinates without semantic information (e.g., Point of Interest (POI)). To make those unlabeled records associate with more information for further applications, it is of great importance to annotate the original data with POIs information based on the external context. Nevertheless, semantic annotation of mobility records is challenging due to three aspects: the complex relationship among multiple domains of context, the sparsity of mobility records, and difficulties in balancing personal preference and crowd preference. To address these challenges, we propose CAP, a context-aware personalized semantic annotation model, where we use a Bayesian mixture model to model the complex relationship among five domains of context—location, time, POI category, personal preference, and crowd preference. We evaluate our model on two real-world datasets, and demonstrate that our proposed method significantly outperforms the state-of-the-art algorithms by over 11.8%.

Human mobility prediction is of great importance for a wide spectrum of location-based applications. However, predicting mobility is not trivial because of four challenges: 1) the complex sequential transition regularities exhibited with time-dependent and high-order nature; 2) the multi-level periodicity of human mobility; 3) the heterogeneity and sparsity of the collected trajectory data; and 4) the complicated semantic motivation behind the mobility. In this paper, we propose DeepMove, an attentional recurrent network for mobility prediction from lengthy and sparse trajectories. In DeepMove, we first design a multi-modal embedding recurrent neural network to capture the complicated sequential transitions by jointly embedding the multiple factors that govern human mobility. Then, we propose a historical attention model with two mechanisms to capture the multi-level periodicity in a principle way, which effectively utilizes the periodicity nature to augment the recurrent neural network for mobility prediction. Furthermore, we design a context adaptor to capture the semantic effects of Point-Of-Interest (POI)-based activity and temporal factor (e.g., dwell time). Finally, we use the multi-task framework to encourage the model to learn comprehensive motivations with mobility by introducing the task of the next activity type prediction and the next check-in time prediction. We perform experiments on four representative real-life mobility datasets, and extensive evaluation results demonstrate that our model outperforms the state-of-the-art models by more than 10 percent. Moreover, compared with the state-of-the-art neural network models, DeepMove provides intuitive explanations into the prediction and sheds light on interpretable mobility prediction.

Online services are playing critical roles in almost all aspects of users’ life. Users usually have multiple online identities (IDs) in different online services. In order to fuse the separated user data in multiple services for better business intelligence, it is critical for service providers to link online IDs belonging to the same user. On the other hand, the popularity of mobile networks and GPS-equipped smart devices have provided a generic way to link IDs, i.e., utilizing themobility tracesof IDs. However, linking IDs based on their mobility traces has been a challenging problem due to the highly heterogeneous, incomplete and noisy mobility data across services. In this paper, we proposeDPLink, an end-to-end deep learning based framework, to complete the user identity linkage task for heterogeneous mobility data collected from different services with different properties.DPLinkis made up by afeature extractorincluding a location encoder and a trajectory encoder to extract representative features from trajectory and acomparatorto compare and decide whether to link two trajectories as the same user. Particularly, we propose a pre-training strategy with a simple task to train theDPLinkmodel to overcome the training difficulties introduced by the highly heterogeneous nature of different source mobility data. Besides, we introduce a multi-modal embedding network and a co-attention mechanism inDPLinkto deal with the low-quality problem of mobility data. By conducting extensive experiments on two real-life ground-truth mobility datasets with eight baselines, we demonstrate thatDPLinkoutperforms the state-of-the-art solutions by more than 15 percent in terms of hit-precision. Moreover, it is expandable to add external geographical context data and works stably with heterogeneous noisy mobility traces.

Social commerce, which is different from traditional e-commerce where people purchase products via initiative searching or recommendations from the platform, transforms a social community into an inclusive place to do business by enabling people to share products with their friends. A user (sharer), can share a link of a product to their social-connected friends (receiver). Once a receiver purchases the product, the sharer can earn commission provided by the platform. To promote sales, the platform can also assist sharers by providing product candidates which are more likely to be purchased during the social sharing. We define this task of generating sharing suggestions as item recommendation for word-of-mouth scenario, and to the best of our knowledge, this is a new task that has never been explored. In this article, we propose aTriM(short forTriad based word-of-Mouth recommendation) model that can capture both the sharer’s influence and the receiver’s interest at the same time, which are two significant factors that determine whether the receiver will buy the product or not. Furthermore, with joint learning on two parts of interaction data to address data sparsity issue, our proposed TriM-Joint further improves the recommendation performance. By conducting experiments, we show that our proposed models achieve the best results compared to state-of-the-art models with significant improvements by at least$7.4\% \sim 14.4\%$respectively.

Social recommendation, which utilizes social relations to enhance recommender systems, has been gaining increasing attention recently with the rapid development of online social networks. Existing social recommendation methods are based on the assumption, so-calledsocial-trust, that users’ preference or decision is influenced by their social-connected friends’ purchase behaviors. However, they assume that the influences of social relationships are always the same, which violates the fact that users are likely to share preference on different products with different friends. More precisely, friends’ behaviors do not necessarily affect a user’s preferences, and the influence is diverse among different items. In this paper, we contribute a new solution, CSR (short forCharacterizedSocialRegularization) model by designing a universal regularization term for modeling variable social influence. This regularization term captures the finely grained similarity of social-connected friends. We further introduce two variants of our model with different optimization manners. Our proposed model can be applied to both explicit and implicit interaction due to its high generality. Extensive experiments on three real-world datasets demonstrate that our CSR can outperform state-of-the-art social recommendation methods. Further experiments show that CSR can improve recommendation performance for those users with sparse social relations or behavioral interactions.

The online retail market shows a sharp increase in traffic during holiday sales. The ability to distinguish customers who will likely purchase is critical for provisioning traffic and for providing cost-effective promotions. This paper uniquely studies the browsing and purchasing behaviors of online shoppers during a yearly sale event in China, the world’s largest online marketplace. Based on 31 million action logs gathered from wide residential areas, we characterize the steps leading to purchases and determine their precursors. We investigate the effect of time (e.g., date, time of date), environment (e.g., platform, viewed category), and action (e.g., session time, clicks, sequence) on purchases. Action cues from shopping behaviors can be used for early detection. While most shoppers start with strong intentions to purchase, yet the moment of ordering comes rather impulsively within 30 seconds to several minutes of browsing. The predictive accuracy reaches as a high AUC of 0.924. The findings in this paper provide an understanding of traffic during mega sale events that can help online shops plan and provide a better user experience for upcoming shopping festivals.

Obtaining crowd flow distribution with recognized human intention is extremely valuable for a series of applications for metropolitan cities. Previous solutions look at spatial correlation and temporal periodicity based on historical crowd flow information to calculate future crowd flow distribution. However, these mechanisms cannot recognize the intention behind crowd flow. We address this problem by leveraging a key insight – people's intention behind their movement is highly correlated with the point-of-interest (POI) distribution of the corresponding regions and adjacent regions. Therefore, we proposeDeepFlowGento model the complicated relationship between crowd flow, POI, check-ins, and time to generate intention-aware crowd flow. Specifically, we solve the conflict between dynamic crowd flow and static POI distribution by fusing the information in both time and POI domains. Besides, we employ a sequence of residual blocks inDeepFlowGento address the challenges of modeling the diverse temporal rhythms and heterogeneous influence of POI. Furthermore, we examine the generated intention-aware crowd flow from two aspects to substantiate the reasonability ofDeepFlowGen. Extensive experiments demonstrate that our model outperforms the state-of-the-art solutions by at most 30 percent in terms of NRMSE of total crowd flow. Moreover, the correlation between the generated intention-aware crowd flow and the check-in distribution across different categories of POIs is as high as 0.90 and 0.80 in Beijing and Shanghai. Combined with extensive case studies, we demonstrate the strong ability of our model in generating intention-aware crowd flow.

As a fundamental component in map service, map matching is of great importance for many trajectory-based applications, e.g., route optimization, traffic scheduling, and fleet management. In practice, Hidden Markov Model and its variants are widely used to provide accurate and efficient map matching service. However, HMM-based methods fail to utilize the knowledge (e.g., the mobility pattern) of enormous trajectory big data, which are useful for intelligent map matching. Furthermore, with many following-up works, they are still easily influenced by the common noisy and sparse records in the reality. In this paper, we revisit the map matching task from the data perspective and propose to utilize the great power of massive data and deep learning to solve these problems. Based on the seq2seq learning framework, we build a trajectory2road model with attention mechanism to map the sparse and noisy trajectory into the accurate road network. Different from previous algorithms, our deep learning based model complete the map matching in the latent space, which provides the high tolerance to the noisy trajectory and also enhances the matching with the knowledge of mobility pattern. Extensive experiments demonstrate that the proposed model outperforms the widely used HMM-based methods by more than 10 percent (absolute accuracy) in various situations especially the noisy and sparse settings.

With the prevalence of smartphones, people have left abundant behavior records in cyberspace. Discovering and understanding individuals’ cyber activities can provide useful implications for policymakers, service providers, and app developers. In this paper, we propose a framework to discover daily cyber activity patterns across people's mobile app usage. The framework first segments app usage traces into short time windows and then applies a probabilistic topic model to infer users’ cyber activities in each window. By constructing and exploring the coherence of users’ activity sequences, the framework can identify individuals’ daily patterns. Next, the framework uses a hierarchical clustering algorithm to recognize the common patterns across diverse groups of individuals. We apply the framework on a large-scale and real-world dataset, consisting of 653,092 users with 971,818,946 usage records of 2,000 popular mobile apps. Our analysis shows that people usually follow yesterday's activity patterns, but the patterns tend to deviate as the time-lapse increases. We also discover five common daily cyber activity patterns, including afternoon reading, nightly entertainment, pervasive socializing, commuting, and nightly socializing. Our findings have profound implications on identifying the demographics of users and their lifestyles, habits, service requirements, and further detecting other disrupting trends such as working overtime and addiction to the game and social media.

Internet of Thing (IoT) devices are rapidly becoming an indispensable part of our life with their increasing deployment in many promising areas, including tele-health, smart city, intelligent agriculture. Understanding the mobility of IoT devices is essential to improve quality of service in IoT applications, such as route planning in logistic management, infrastructure deployment, cellular network update and congestion detection in intelligent traffic. Despite its importance, there are not many results pertaining to the mobility of IoT devices. In this article, we aim to answer three research questions: (i) what are the mobility patterns of IoT device? (ii) what are the differences between IoT device and smartphone mobility patterns? (iii) how the IoT device mobility patterns differ among device types and usage scenarios? We present a comprehensive characterization of IoT device mobility patterns from the perspective of cellular data networks, using a 36-days long signal trace, including 1.5 million IoT devices and 0.425 million smartphones, collected from a nation-wide cellular network in China. We first investigate the basic patterns of IoT devices from two perspectives: temporal and spatial characteristics. Our study finds that IoT device mobility exhibits significantly different patterns compared with smartphones in multiple aspects. For instance, IoT devices move more frequently and have larger radius of gyration. Then we explore the essential mobility of IoT devices by utilizing two models that reveal the nature of human mobility, i.e., exploration and preferential return (EPR) model and entropy based predictability model. We find that IoT devices, with few exceptions, behave totally different from human, and we further derive a new formulation to describe their movement. We also find the gap mobility predictability and predictability limit between IoT and human is not as big as people expected.

A considerable amount of mobility data has been accumulated due to the proliferation of location-based service. Nevertheless, compared with mobility data from transportation systems like the GPS module in taxis, this kind of data is commonly sparse in terms of individual trajectories in the sense that users do not access mobile services and contribute their data all the time. Consequently, the sparsity inevitably weakens the practical value of the data even it has a high user penetration rate. To solve this problem, we propose a novel attentional neural network-based model, named AttnMove, to densify individual trajectories by recovering unobserved locations at a fine-grained spatial-temporal resolution. To tackle the challenges posed by sparsity, we design various intra- and inter- trajectory attention mechanisms to better model the mobility regularity of users and fully exploit the periodical pattern from long-term history. We evaluate our model on two real-world datasets, and extensive results demonstrate the performance gain compared with the state-of-the-art methods. This also shows that, by providing high-quality mobility data, our model can benefit a variety of mobility-oriented down-stream applications.

The COVID-19 global pandemic and resulted lockdown policies have forced education in nearly every country to switch from a traditional co-located paradigm to a pure online “distance learning from home” paradigm. Lying in the center of this learning paradigm shift is the emergence and wide adoption of distance communication tools and live streaming platforms for education. Here, we present a mixed-methods study on live streaming based education experience during the COVID-19 pandemic. We focus our analysis on Chinese higher education, carried out semi-structured interviews on 30 students, and 7 instructors from diverse colleges and disciplines, meanwhile launched a large-scale survey covering 6291 students and 1160 instructors in one leading Chinese university. Our study not only reveals important design guidelines and insights to better support current remote learning experience during the pandemic, but also provides valuable implications towards constructing future collaborative education supporting systems and experience after pandemic.

Fine-grained population distribution data is of great importance for many applications, e.g., urban planning, traffic scheduling, epidemic modeling, and risk control. However, due to the limitations of data collection, including infrastructure density, user privacy, and business security, such fine-grained data is hard to collect and usually, only coarse-grained data is available. Thus, obtaining fine-grained population distribution from coarse-grained distribution becomes an important problem. To tackle this problem, existing methods mainly rely on sufficient fine-grained ground truth for training, which is not often available for the majority of cities. That limits the applications of these methods and brings the necessity to transfer knowledge between data-sufficient source cities to data-scarce target cities.

We propose a novel automated deep learning framework, namely Automated Spatio-Temporal Dual Graph Convolutional Networks (Auto-STDGCN), for travel time estimation. Specifically, a hierarchical neural architecture search approach is introduced to capture the joint spatio-temporal correlations of intersections and road segments, whose search space is composed of internal and external search space. In the internal search space, spatial graph convolution and temporal convolution operations are adopted to capture the spatio-temporal correlations of the dual graphs. In the external search space, the node-wise and edge-wise graph convolution operations from the internal architecture search are built to capture the interaction patterns between the intersections and road segments. We conduct several experiments on two real-world datasets, and the results demonstrate that Auto-STDGCN is significantly superior to the state-of-art methods.

A large-scale system for obtaining fine-grained vehicle trajectories is becoming increasingly important because it lays a solid foundation for a wide range of downstream applications, such as urban traffic optimization, road network profiling, route planning, etc. Traditional methods recover the trajectories from GPS data from apps or coarse-grained traces collected from base stations, which are costly and, more importantly, only cover limited vehicles on the road. Thus, they are not applicable to downstream tasks. To fill this gap, we explore the possibility of recovering vehicle trajectories from the video data recorded by widely deployed traffic cameras. The major challenges lie in the quality of the captured image, low sampling rate, and unbalanced temporal and spatial distribution. To address these challenges, we propose a general system to recover vehicle trajectories at the level of the road intersection, where a novel iterative framework is developed to combine both vehicle clustering and trajectory recovery tasks, which improve their performance simultaneously. The key motivation is that vehicle clustering based on visual features can provide essential discrete points for trajectory recovery, while the recovered routes can introduce spatial-temporal constraints to the initial vehicle clusters for de-noising the false results and complement the missing results. To prove the feasibility of our framework, we collect and plan to release a city-scale traffic camera dataset consisting of 24 hours of videos from 673 cameras across 1,106 intersections. To the best of our knowledge, this benchmark is the first to contain the ground truth of vehicle trajectories with a wide range of spatial and temporal coverage in an urban environment. We conduct extensive experiments and analysis on datasets of different scales to demonstrate the robustness of our framework. Last but not least, we have already deployed the whole system in the business applications of SenseTime, China, including traffic signal control and traffic flow analysis. We highly expect this dataset to further facilitate the research in this field and contribute more to traffic optimization systems in the real world.

Recently, deep learning-based image enhancement algorithms achieved state-of-the-art (SOTA) performance on several publicly available datasets. However, most existing methods fail to meet practical requirements either for visual perception or for computation efficiency, especially for high-resolution images. In this paper, we propose a novel real-time image enhancer via learnable spatial-aware 3dimentional lookup tables(3D LUTs), which well considers global scenario and local spatial information. Specifically, we introduce a light weight two-head weight predictor that has two outputs. One is a 1D weight vector used for image-level scenario adaptation, the other is a 3D weight map aimed for pixel-wise category fusion. We learn the spatial-aware 3D LUTs and fuse them according to the aforementioned weights in an end-to-end manner. The fused LUT is then used to transform the source image into the target tone in an efficient way. Extensive results show that our model outperforms SOTA image enhancement methods on public datasets both subjectively and objectively, and that our model only takes about 4ms to process a 4K resolution image on one NVIDIA V100 GPU.

Group buying, as an emerging form of purchase in social e-commerce websites, such as Pinduoduo1, has recently achieved great success. In this new business model, users, initiator, can launch a group and share products to their social networks, and when there are enough friends, participants, join it, the deal is clinched. Group-buying recommendation for social e-commerce, which recommends an item list when users want to launch a group, plays an important role in the group success ratio and sales. However, designing a personalized recommendation model for group buying is an entirely new problem that is seldom explored. In this work, we take the first step to approach the problem of group-buying recommendation for social e-commerce and develop a GBGCN method (short for Group-Buying Graph Convolutional Network). Considering there are multiple types of behaviors (launch and join) and structured social network data, we first propose to construct directed heterogeneous graphs to represent behavioral data and social networks. We then develop a graph convolutional network model with multi-view embedding propagation, which can extract the complicated high-order graph structure to learn the embeddings. Last, since a failed group-buying implies rich preferences of the initiator and participants, we design a double-pairwise loss function to distill such preference signals. We collect a real-world dataset of group-buying and conduct experiments to evaluate the performance. Empirical results demonstrate that our proposed GBGCN can significantly outperform baseline methods by 2.69%-7.36%. The codes and the dataset are released at https://github.com/Sweetnow/group-buying-recommendation.

Traffic prediction is a crucial task in many real-world applications. The task is challenging due to the implicit and dynamic spatio-temporal dependencies among traffic data. On the one hand, the spatial dependencies among traffic flows are latent and fluctuate with environmental conditions. On the other hand, the temporal dependencies among traffic flows also vary significantly over time and locations. In this paper, we propose Adaptive Spatio-Temporal Convolutional Network (ASTCN) to tackle these challenges. First, we propose a spatial graph learning module that learns the dynamic spatial relations among traffic data based on multiple influential factors. Furthermore, we design an adaptive temporal convolution module that captures complex temporal traffic dependencies with environment-aware dynamic filters. We conduct extensive experiments on three real-world traffic datasets. The results demonstrate that the proposed ASTCN consistently outperforms state-of-the-arts.

Collaborative filtering (CF), as a fundamental approach for recommender systems, is usually built on the latent factor model with learnable parameters to predict users' preferences towards items. However, designing a proper CF model for a given data is not easy, since the properties of datasets are highly diverse. In this paper, motivated by the recent advances in automated machine learning (AutoML), we propose to design a data-specific CF model by AutoML techniques. The key here is a new framework that unifies state-of-the-art (SOTA) CF methods and splits them into disjoint stages of input encoding, embedding function, interaction function, and prediction function. We further develop an easy-to-use, robust, and efficient search strategy, which utilizes random search and a performance predictor for efficient searching within the above framework. In this way, we can combinatorially generalize data-specific CF models, which have not been visited in the literature, from SOTA ones. Extensive experiments on five real-world datasets demonstrate that our method can consistently outperform SOTA ones for various CF tasks. Further experiments verify the rationality of the proposed framework and the efficiency of the search strategy. The searched CF models can also provide insights for exploring more effective methods in the future.

Facing the outbreak of COVID-19, shortage in medical resources becomes increasingly outstanding. Therefore, efficient strategies for medical resource allocation are urgently called for. Reinforcement learning (RL) is powerful for decision making, but three key challenges exist in solving this problem via RL: (1) complex situation and countless choices for decision making in the real world; (2) only imperfect information are available due to the latency of pandemic spreading; (3) limitations on conducting experiments in real world since we cannot set pandemic outbreaks arbitrarily. In this paper, we propose a hierarchical reinforcement learning method with a corresponding training algorithm. We design a decomposed action space to deal with the countless choices to ensure efficient and real time strategies. We also design a recurrent neural network based framework to utilize the imperfect information obtained from the environment. We build a pandemic spreading simulator based on real world data, serving as the experimental platform. We conduct extensive experiments and the results show that our method outperforms all the baselines, which reduces infections and deaths by 14.25% on average.

For online life service platforms, such as Meituan, user consumption intention, as the internal driving force of consumption behaviors, plays a significant role in understanding and predicting users' demand and purchase. However, user consumption intention prediction is quite challenging. Different from consumption behaviors, consumption intention is implicit and always not reflected by behavioral data. Moreover, it is affected by both user intrinsic preference and spatio-temporal context. To overcome these challenges, in Meituan, we design a real-world system consisting of two stages, intention detection and prediction. Specifically, at the intention-detection stage, we combine the knowledge of human experts and consumption information to obtain explicit intentions and match consumption with intentions based on user review data. At the intention-prediction stage, to collectively exploit the rich heterogeneous influencing factors, we design a graph neural network-based intention prediction model GRIP, which can capture user intrinsic preference and spatio-temporal context. Extensive offline evaluations demonstrate that our prediction model outperforms the best baseline by 10.26% and 33.28% for two metrics and online A/B tests on millions of users validate the effectiveness of our system.

Deep sparse networks (DSNs), of which the crux is exploring the high-order feature interactions, have become the state-of-the-art on the prediction task with high-sparsity features. However, these models suffer from low computation efficiency, including large model size and slow model inference, which largely limits these models' application value. In this work, we approach this problem with neural architecture search by automatically searching the critical component in DSNs, the feature-interaction layer. We propose a distilled search space to cover the desired architectures with fewer parameters. We then develop a progressive search algorithm for efficient search on the space and well capture the order-priority property in sparse prediction tasks. Experiments on three real-world benchmark datasets show promising results of PROFIT in both accuracy and efficiency. Further studies validate the feasibility of our designed search space and search algorithm.

Distinguishing the automorphic equivalence of nodes in a graph plays an essential role in many scientific domains, e.g., computational biologist and social network analysis. However, existing graph neural networks (GNNs) fail to capture such an important property. To make GNN aware of automorphic equivalence, we first introduce a localized variant of this concept --- ego-centered automorphic equivalence (Ego-AE). Then, we design a novel variant of GNN, i.e., GRAPE, that uses learnable AE-aware aggregators to explicitly differentiate the Ego-AE of each node's neighbors with the aids of various subgraph templates. While the design of subgraph templates can be hard, we further propose a genetic algorithm to automatically search them from graph data. Moreover, we theoretically prove that GRAPE is expressive in terms of generating distinct representations for nodes with different Ego-AE features, which fills in a fundamental gap of existing GNN variants. Finally, we empirically validate our model on eight real-world graph data, including social network, e-commerce co-purchase network, and citation network, and show that it consistently outperforms existing GNNs. The source code is public available at https://github.com/tsinghua-fib-lab/GRAPE.

Sequential recommendation aims to leverage users' historical behaviors to predict their next interaction. Existing works have not yet addressed two main challenges in sequential recommendation. First, user behaviors in their rich historical sequences are often implicit and noisy preference signals, they cannot sufficiently reflect users' actual preferences. In addition, users' dynamic preferences often change rapidly over time, and hence it is difficult to capture user patterns in their historical sequences. In this work, we propose a graph neural network model called SURGE (short forSeqUential Recommendation with Graph neural nEtworks) to address these two issues. Specifically, SURGE integrates different types of preferences in long-term user behaviors into clusters in the graph by re-constructing loose item sequences into tight item-item interest graphs based on metric learning. This helps explicitly distinguish users' core interests, by forming dense clusters in the interest graph. Then, we perform cluster-aware and query-aware graph convolutional propagation and graph pooling on the constructed graph. It dynamically fuses and extracts users' current activated core interests from noisy user behavior sequences. We conduct extensive experiments on both public and proprietary industrial datasets. Experimental results demonstrate significant performance gains of our proposed method compared to state-of-the-art methods. Further studies on sequence length confirm that our method can model long behavioral sequences effectively and efficiently.

N-ary relational knowledge bases (KBs) represent knowledge with binary and beyond-binary relational facts. Especially, in an n-ary relational fact, the involved entities play different roles, e.g., the ternary relation PlayCharacterIn consists of three roles, Actor, Character and Movie. However, existing approaches are often directly extended from binary relational KBs, i.e., knowledge graphs, while missing the important semantic property of role. Therefore, we start from the role level, and propose a Role-Aware Modeling, RAM for short, for facts in n-ary relational KBs. RAM explores a latent space that contains basis vectors, and represents roles by linear combinations of these vectors. This way encourages semantically related roles to have close representations. RAM further introduces a pattern matrix that captures the compatibility between the role and all involved entities. To this end, it presents a multilinear scoring function to measure the plausibility of a fact composed by certain roles and entities. We show that RAM achieves both theoretical full expressiveness and computation efficiency, which also provides an elegant generalization for approaches in binary relational KBs. Experiments demonstrate that RAM outperforms representative baselines on both n-ary and binary relational datasets.

Customer value is essential for successful customer relationship management. Although growing evidence suggests that customers’ purchase decisions can be influenced by social relationships, social influence is largely overlooked in previous research. In this work, we fill this gap with a novel framework — Motif-based Multi-view Graph Attention Networks with Gated Fusion (MAG), which jointly considers customer demographics, past behaviors, and social network structures. Specifically, (1) to make the best use of higher-order information in complex social networks, we design a motif-based multi-view graph attention module, which explicitly captures different higher-order structures, along with the attention mechanism auto-assigning high weights to informative ones. (2) To model the complex effects of customer attributes and social influence, we propose a gated fusion module with two gates: one depicts the susceptibility to social influence and the other depicts the dependency of the two factors. Extensive experiments on two large-scale datasets show superior performance of our model over the state-of-the-art baselines. Further, we discover that the increase of motifs does not guarantee better performances and identify how motifs play different roles. These findings shed light on how to understand socio-economic relationships among customers and find high-value customers.

The phenomenal success of the newly-emerging social e-commerce has demonstrated that utilizing social relations is becoming a promising approach to promote e-commerce platforms. In this new scenario, one of the most important problems is to predict the value of a community formed by closely connected users in social networks due to its tremendous business value. However, few works have addressed this problem because of 1) its novel setting and 2) its challenging nature that the structure of a community has complex effects on its value. To bridge this gap, we develop a Multi-scale Structure-aware Community value prediction network (MSC) that jointly models the structural information of different scales, including peer relations, community structure, and inter-community connections, to predict the value of given communities. Specifically, we first proposed a Masked Edge Learning Graph Convolutional Network (MEL-GCN) based on a novel masked propagation mechanism to model peer influence. Then, we design a Pair-wise Community Pooling (PCPool) module to capture critical community structures. Finally, we model the inter-community connections by distinguishing intra-community edges from inter-community edges and employing a Multi-aggregator Framework (MAF). Extensive experiments on a large-scale real-world social e-commerce dataset demonstrate our method’s superior performance over state-of-the-art baselines, with a relative performance gain of 11.40%, 10.01%, and 10.97% in MAE, RMSE, and NRMSE, respectively. Further ablation study shows the effectiveness of our designed components. Our code and dataset are available1.

These years much effort has been devoted to improving the accuracy or relevance of the recommendation system. Diversity, a crucial factor which measures the dissimilarity among the recommended items, received rather little scrutiny. Directly related to user satisfaction, diversification is usually taken into consideration after generating the candidate items. However, this decoupled design of diversification and candidate generation makes the whole system suboptimal. In this paper, we aim at pushing the diversification to the upstream candidate generation stage, with the help of Graph Convolutional Networks (GCN). Although GCN based recommendation algorithms have shown great power in modeling complex collaborative filtering effect to improve the accuracy of recommendation, how diversity changes is ignored in those advanced works. We propose to perform rebalanced neighbor discovering, category-boosted negative sampling and adversarial learning on top of GCN. We conduct extensive experiments on real-world datasets. Experimental results verify the effectiveness of our proposed method on diversification. Further ablation studies validate that our proposed method significantly alleviates the accuracy-diversity dilemma.

Recommendation models are usually trained on observational interaction data. However, observational interaction data could result from users’ conformity towards popular items, which entangles users’ real interest. Existing methods tracks this problem as eliminating popularity bias, e.g., by re-weighting training samples or leveraging a small fraction of unbiased data. However, the variety of user conformity is ignored by these approaches, and different causes of an interaction are bundled together as unified representations, hence robustness and interpretability are not guaranteed when underlying causes are changing. In this paper, we present DICE, a general framework that learns representations where interest and conformity are structurally disentangled, and various backbone recommendation models could be smoothly integrated. We assign users and items with separate embeddings for interest and conformity, and make each embedding capture only one cause by training with cause-specific data which is obtained according to the colliding effect of causal inference. Our proposed methodology outperforms state-of-the-art baselines with remarkable improvements on two real-world datasets on top of various backbone models. We further demonstrate that the learned embeddings successfully capture the desired causes, and show that DICE guarantees the robustness and interpretability of recommendation.

Driven by the soaring traffic demand and the growing diversity of mobile services, wireless networks are evolving to be increasingly dense and heterogeneous. Accordingly, in such large-scale and complicated wireless networks, optimal controlling is reaching unprecedented levels of complexity while its traditional solutions of handcrafted offline algorithms become inefficient due to high complexity, low robustness, and high overhead. Therefore, reinforcement learning (RL), which enables network entities to learn from their actions and consequences in the interactive network environment, attracts significant attention. In this article, we comprehensively review the applications of RL in wireless networks from a layering perspective. First, we present an overview of the principle, fundamentals, and several advanced models of RL. Then, we review the up-to-date applications of RL in various functionality blocks of different network layers, ranging from the low-level physical layer to the high-level application layer. Finally, we outline a broad spectrum of challenges, open issues, and future research directions of RL-empowered wireless networks.

Privacy leakage of Internet of Things (IoT) has become a great challenge with the popularity of IoT services through mobile networks, such as smart homes, wearables, and healthcare. While previous work summarized general structures to analyze IoT privacy and provide case studies of specific devices or scenarios, it is still challenging to conduct a comprehensive and systematic quantification study of large-scale IoT privacy leakage in real world. To combine systematic analyses with real-world measurements, we provide a method to quantify IoT privacy leakage on a large-scale mobile network traffic data set containing 47651 IoT devices. We generate privacy fingerprints and attribute them to a privacy quantification framework. The framework is constructed based on the semantics of multiple privacy sensitive markers selected from the traffic along with the involved network entity types in IoT (i.e., user, device, and platform), and the fingerprints are generated from sensitive information extracted in the traffic via their markers. Our quantification shows that IoT users, devices, and platforms have considerable risks, respectively. Moreover, IoT devices have a larger scale of privacy leakage than users and platforms, and they perform different daily patterns on privacy leakage following their working conditions. In addition, we present three case studies on the leakage of location information, application calling, and voice service, which illustrate that a third party can profile a network entity in both cyberspace and physical space.

The outbreak of Covid-19 changed the world as well as human behavior. In this article, we study the impact of Covid-19 on smartphone usage. We gather smartphone usage records from a global data collection platform called Carat, including the usage of mobile users in North America from November 2019 to April 2020. We then conduct the first study on the differences in smartphone usage across the outbreak of Covid-19. We discover that Covid-19 leads to a decrease in users' smartphone engagement and network switches, but an increase in WiFi usage. Also, its outbreak causes new typical diurnal patterns of both memory usage and WiFi usage. Additionally, we investigate the correlations between smartphone usage and daily confirmed cases of Covid-19. The results reveal that memory usage, WiFi usage, and network switches of smartphones have significant correlations, whose absolute values of Pearson coefficients are greater than 0.8. Moreover, smartphone usage behavior has the strongest correlation with the Covid-19 cases occurring after it, which exhibits the potential of inferring outbreak status. By conducting extensive experiments, we demonstrate that for the inference of outbreak stages, both Macro-F1 and Micro-F1 can achieve over 0.8. Our findings explore the values of smartphone usage data for fighting against the epidemic.

Accurate human mobility prediction is important for many applications in wireless networks, including intelligent content caching and prefetching, network optimization, etc. However, modeling mobility patterns has been a challenging problem due to the complicated human mobility patterns influenced by the long-term correlation with historical trajectories and context information, and the long time interval between consecutive mobility records. In this paper, we integrate the novel attention technique into the Markov model to predict future locations. This model allows us to consider the time context of users' mobility behavior, which overcomes the disadvantage of the traditional Markov model in modeling the periodicity of trajectories. We conducted extensive evaluations using two different mobility datasets, which involve over 20,000 users. Our evaluations show that our proposed solution outperforms the state-of-the-art algorithms by over 6.6% on average. In addition, compared with the method based on deep recurrent neural networks achieving the same performance, our proposed model runs significantly faster, i.e., reducing the computation time by over 170 times, demonstrating the effeteness of our proposed model.

As an emerging business phenomenon especially in China, instant messaging (IM) based social commerce is growing increasingly popular, attracting hundreds of millions of users and is becoming one important way where people make everyday purchases. Such platforms embed shopping experiences within IM apps, e.g., WeChat, WhatsApp, where real-world friends post and recommend products from the platforms in IM group chats and quite often form lasting recommending/buying relationships. How and why do users engage in IM based social commerce? Do such platforms create novel experiences that are distinct from prior commerce? And do these platforms bring changes to user social lives and relationships? To shed light on these questions, we launched a qualitative study where we carried out semi-structured interviews on 12 instant messaging based social commerce users in China. We showed that IM based social commerce: 1) enables more reachable, cost-reducing, and immersive user shopping experience, 2) shapes user decision-making process in shopping through pre-existing social relationship, mutual trust, shared identity, and community norm, and 3) creates novel social interactions, which can contribute to new tie formation while maintaining existing social relationships. We demonstrate that all these unique aspects link closely to the characteristics of IM platforms, as well as the coupling of user social and economic lives under such business model. Our study provides important research and design implications for social commerce, and decentralized, trusted socio-technical systems in general.

The recommender system (RS), as a computer-supported information filtering system, is ubiquitous and influences what we eat, watch, or even like. In online RS, interactions between users and the system form a feedback loop: users take actions based on the recommendations provided by RS, and RS updates its recommendations accordingly. As such interactions increase, the issue of recommendation homogeneity intensifies, which significantly impairs user experience. In the face of this long-standing issue, the newly-emerging social e-commerce offers a new solution -- bringing friends' recommendations into the loop (friend-in-the-loop). In this paper, we conduct an exploratory study on the benefits of friend-in-the-loop through mixed methods on a leading social e-commerce platform in China, Beidian. We reveal that friend-in-the-loop provides users with more accurate and diverse recommendations than merely RS, and significantly alleviates algorithmic homogeneity. Moreover, our qualitative results demonstrate that the introduction of friends' external knowledge, consumers' trust, and empathy accounts for these benefits. Overall, we elaborate that friend-in-the-loop comprehensively benefits both users and RS, and it is a promising HCI-based solution to recommendation homogeneity, which offers insightful implications on designing future human-algorithm collaboration models.

Edge intelligence refers to a set of connected systems and devices for data collection, caching, processing, and analysis proximity to where data are captured based on artificial intelligence. Edge intelligence aims at enhancing data processing and protects the privacy and security of the data and users. Although recently emerged, spanning the period from 2011 to now, this field of research has shown explosive growth over the past five years. In this article, we present a thorough and comprehensive survey of the literature surrounding edge intelligence. We first identify four fundamental components of edge intelligence, i.e., edge caching, edge training, edge inference, and edge offloading based on theoretical and practical results pertaining to proposed and deployed systems. We then aim for a systematic classification of the state of the solutions by examining research results and observations for each of the four components and present a taxonomy that includes practical problems, adopted techniques, and application goals. For each category, we elaborate, compare, and analyze the literature from the perspectives of adopted techniques, objectives, performance, advantages and drawbacks, and so on. This article provides a comprehensive survey of edge intelligence and its application areas. In addition, we summarize the development of the emerging research fields and the current state of the art and discuss the important open issues and possible theoretical and technical directions.

Video accounts for a large proportion of traffic on the Internet. Understanding its geographical viewing patterns is extremely valuable for the design of Internet ecosystems for content delivery, recommendation and ads. While previous works have addressed this problem at coarse-grain scales (e.g., national), the urban-scale geographical patterns of video access have never been revealed. To this end, this article aims to investigate the problem that whether there exists distinct viewing patterns among the neighborhoods of a large-scale city. To achieve this, we need to address several challenges including unknown of patterns profiles, complicate urban neighborhoods, and comprehensive viewing features. The contributions of this article include two aspects. First, we design a framework to automatically identify geographical video viewing patterns in urban neighborhoods. Second, by using a dataset of two months real video requests in Shanghai collected from one major ISP of China, we make a rigorous analysis of video viewing patterns in Shanghai. Our study reveals the following important observations. First, there exists four prevalent and distinct patterns of video access behavior in urban neighborhoods, which are corresponding to four different geographical contexts: downtown residential, office, suburb residential and hybrid regions. Second, there exists significant features that distinguish different patterns, e.g., the probabilities of viewing TV plays at midnight, and viewing cartoons at weekends can distinguish the two viewing patterns corresponding to downtown and suburb regions.

Understanding the linkability of online user identifiers (IDs) is critical to both service providers (for business intelligence) and individual users (for assessing privacy risks). Existing methods are designed to match IDs across two services but face key challenges of matching multiple services in practice, particularly when users have multiple IDs per service. In this article, we propose a novel system to link IDs across multiple services by exploring the spatial-temporal features of user activities, of which the core idea is that the same user's online IDs are more likely to repeatedly appear at the same location. Specifically, we first utilize a contact graph to capture the “co-location” of all IDs across multiple services. Based on this graph, we propose a set-wise matching algorithm to discover candidate ID sets and use Bayesian inference to generate confidence scores for candidate ranking, which is proved to be optimal. We evaluate our system using two real-world ground-truth datasets from an Internet service provider (4 services, 815K IDs) and Twitter-Foursquare (2 services, 770 IDs). Extensive results show that our system significantly outperforms the state-of-the-art algorithms in accuracy (AUC is higher by 0.1–0.2), and it is highly robust against data quality, matching order, and number of services.

introduction Share on ACM TIST Special Issue on Deep Learning for Spatio-Temporal Data: Part 1 Authors: Senzhang Wang Central South University, Changsha, China Central South University, Changsha, ChinaSearch about this author , Junbo Zhang JD Intelligent Cities Research; JD iCity, JD Tech, Beijing, China JD Intelligent Cities Research; JD iCity, JD Tech, Beijing, ChinaSearch about this author , Yanjie Fu University of Central Florida, Orlando, U.S.A. University of Central Florida, Orlando, U.S.A.Search about this author , Yong Li Tsinghua University, Beijing, China Tsinghua University, Beijing, ChinaSearch about this author Authors Info & Claims ACM Transactions on Intelligent Systems and TechnologyVolume 12Issue 6December 2021 Article No.: 67pp 1–3https://doi.org/10.1145/3495188Online:16 December 2021Publication History 0citation122DownloadsMetricsTotal Citations0Total Downloads122Last 12 Months122Last 6 weeks23 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Both app developers and service providers have strong motivations to understandwhenandwherecertain apps are used by users. However, it has been a challenging problem due to the highly skewed and noisy app usage data. Moreover, apps are regarded as independent items in existing studies, which fail to capture the hidden semantics in app usage traces. In this article, we propose App2Vec, a powerful representation learning model to learn the semantic embedding of apps with the consideration of spatio-temporal context. Based on the obtained semantic embeddings, we develop a probabilistic model based on the Bayesian mixture model and Dirichlet process to capturewhen,where, andwhatsemantics of apps are used to predict the future usage. We evaluate our model using two different app usage datasets, which involve over 1.7 million users and 2,000+ apps. Evaluation results show that our proposed App2Vec algorithm outperforms the state-of-the-art algorithms in app usage prediction with a performance gap of over 17.0%.

Crowd flow prediction is an essential task benefiting a wide range of applications for the transportation system and public safety. However, it is a challenging problem due to the complex spatio-temporal dependence and the complicated impact of urban structure on the crowd flow patterns. In this article, we propose a novel framework, 3- D imensional G raph C onvolution N etwork (3DGCN), to predict citywide crowd flow. We first model it as a dynamic spatio-temporal graph prediction problem, where each node represents a region with time-varying flows, and each edge represents the origin–destination (OD) flow between its corresponding regions. As such, OD flows among regions are treated as a proxy for the spatial interactions among regions. To tackle the complex spatio-temporal dependence, our proposed 3DGCN can model the correlation among graph spatial and temporal neighbors simultaneously. To learn and incorporate urban structures in crowd flow prediction, we design the GCN aggregator to be learned from both crowd flow prediction and region function inference at the same time. Extensive experiments with real-world datasets in two cities demonstrate that our model outperforms state-of-the-art baselines by 9.6%∼19.5% for the next-time-interval prediction.

Bayesian Personalized Ranking (BPR) is a representative pairwise learning method for optimizing recommendation models. It is widely known that the performance of BPR depends largely on the quality of negative sampler. In this paper, we make two contributions with respect to BPR. First, we find that sampling negative items from the whole space is unnecessary and may even degrade the performance. Second, focusing on the purchase feedback of E-commerce, we propose a negative sampler for BPR by leveraging the additional view data. In our proposed sampler, users' viewed interactions are considered as an intermediate feedback between the purchased and unobserved interactions. We jointly learn the pairwise rankings of user preference among these three types of interactions and design a user-oriented weighting strategy during learning process, which is more effective and flexible. Compared to the vanilla BPR that applies a uniform sampler on all candidates, our view-enhanced sampler enhances BPR with a relative improvement over 36.64 and 16.40 percent on Beibei and Tmall datasets, respectively. Empirical studies demonstrate the importance of considering users' additional feedback when modeling their preference on different items, which can effectively improve the quality of sampled negative items towards learning a better personalized ranking function. Our implementation is available at https://github.com/dingjingtao/NegativeSamplerBPR.

Most existing recommender systems leverage user behavior data of one type only, such as the purchase behavior in E-commerce that is directly related to the business Key Performance Indicator (KPI) of conversion rate. Besides the key behavioral data, we argue that other forms of user behaviors also provide valuable signal, such as views, clicks, adding a product to shopping carts and so on. They should be taken into account properly to provide quality recommendation for users. In this work, we contribute a new solution named short for Neural Multi-Task Recommendation (NMTR) for learning recommender systems from user multi-behavior data. We develop a neural network model to capture the complicated and multi-type interactions between users and items. In particular, our model accounts for the cascading relationship among different types of behaviors (e.g., a user must click on a product before purchasing it). To fully exploit the signal in the data of multiple types of behaviors, we perform a joint optimization based on the multi-task learning framework, where the optimization on a behavior is treated as a task. Extensive experiments on two real-world datasets demonstrate that NMTR significantly outperforms state-of-the-art recommender systems that are designed to learn from both single-behavior data and multi-behavior data. Further analysis shows that modeling multiple behaviors is particularly useful for providing recommendation for sparse users that have very few interactions.

Understanding human mobility benefits numerous applications such as urban planning, traffic control, and city management. Previous work mainly focuses on modeling spatial and temporal patterns of human mobility. However, the semantics of trajectory are ignored, thus failing to model people's motivation behind mobility. In this paper, we propose a novel semantics-aware mobility model that captures human mobility motivation using large-scale semantic-rich spatial-temporal data from location-based social networks. In our system, we first develop a multimodal embedding method to project user, location, time, and activity on the same embedding space in an unsupervised way while preserving original trajectory semantics. Then, we use hidden Markov model to learn latent states and transitions between them in the embedding space, which is the location embedding vector, to jointly consider spatial, temporal, and user motivations. In order to tackle the sparsity of individual mobility data, we further propose a von Mises-Fisher mixture clustering for user grouping so as to learn a reliable and fine-grained model for groups of users sharing mobility similarity. We evaluate our proposed method on two large-scale real-world datasets, where we validate the ability of our method to produce high-quality mobility models. We also conduct extensive experiments on the specific task of location prediction. The results show that our model outperforms state-of-the-art mobility models with higher prediction accuracy and much higher efficiency.

With the ever-increasing urbanization process, systematically modeling people's activities in the urban space is being recognized as a crucial socioeconomic task. It is extremely challenging due to the lack of reliable data and suitable methods, yet the emergence of population-scale urban mobility data sheds new light on it. However, recent works on discovering activity patterns from urban mobility data are still limited in terms of concisely and specifically modeling the temporal dynamics of people's urban activities. To bridge the gap, we present a State-sharing Hidden Markov Model (SSHMM), a novel time-series modeling method that uncovers urban dynamics with massive urban mobility data. SSHMM models the urban dynamics from two aspects. First, it extracts the urban states from the whole city, which captures the volume of population flows as well as the frequency of each type of Point of Interests (PoIs) visited. Second, it characterizes the urban dynamics of each urban region as the state transition on the shared-states, which reveals distinct daily rhythms of urban activities. We evaluate our method via large-scale real-life mobility dataset. The results demonstrate that SSHMM learns semantics-rich urban dynamics, which are highly correlated with the functions of the region. Besides, it recovers the urban dynamics in different time slots with RMSE of 0.0793 when only learn limited states for the whole city, which outperforms the general HMM by 54.2 percent.

As online video service continues to grow in popularity, video content providers compete hard for more eyeball engagement. Some users visit multiple video sites to enjoy videos of their interest while some visit exclusively one site. However, due to the isolation of data, mining and exploiting user behaviors in multiple video websites remain unexplored so far. In this work, we try to model user preferences in six popular video websites with user viewing records obtained from a large ISP in China. The empirical study shows that users exhibit both consistent cross-site interests as well as site-specific interests. To represent this dichotomous pattern of user preferences, we propose a generative model of Multi-site Probabilistic Factorization (MPF) to capture both the cross-site as well as site-specific preferences. Besides, we discuss the design principle of our model by analyzing the sources of the observed site-specific user preferences, namely, site peculiarity and data sparsity. Through conducting extensive recommendation validation, we show that our MPF model achieves the best results compared to several other state-of-the-art factorization models with significant improvements of F-measure by 12.96, 8.24 and 6.88 percent, respectively. Our findings provide insights on the value of integrating user data from multiple sites, which stimulates collaboration between video service providers.

The current explosion of video traffic compels service providers to deploy caches at edge networks. Nowadays, most caching systems store data with a high programming voltage corresponding to the largest possible ‘expiry date’, typically on the order of years, which maximizes the cache damage. However, popular videos rarely exhibit lifecycles longer than a couple of months. Consequently, the programming voltage can instead be adapted to fit the lifecycle and mitigate the cache damage accordingly. In this paper, we propose LiA-cache, a Lifecycle-Aware caching policy for online videos. LiA-cache finds both near-optimal caching retention times and cache eviction policies by optimizing traffic delivery cost and cache damage cost conjointly. We first investigate temporal patterns of video access from a real-world dataset covering 10 million online videos collected by one of the largest mobile network operators in the world. We next cluster the videos based on their access lifecycles and integrate the clustering into a general model of the caching system. Specifically, LiA-cache analyzes videos and caches them depending on their cluster label. Compared to other popular policies in real-world scenarios, LiA-cache can reduce cache damage up to 90 perce, while keeping a cache hit ratio close to a policy purely relying on video popularity.

Human mobility trajectories are increasingly collected by ISPs to assist academic research and commercial applications. Meanwhile, there is a growing concern that individual trajectories can be de-anonymized when the data is shared, using information from external sources (e.g., online social networks). To understand this risk, prior works either estimate the theoretical privacy bound or simulate de-anonymization attacks on synthetically created datasets. However, it is not clear how well the theoretical estimations are preserved in practice. In this article, we collected a large-scale ground-truth trajectory dataset from 2,161,500 users of a cellular network, and two matched external trajectory datasets from a large social network (56,683 users) and a check-in/review service (45,790 users) on the same user population. The two sets of large ground-truth data provide a rare opportunity to extensively evaluate a variety of de-anonymization algorithms (nine in total). We find that their performance in the real-world dataset is far from the theoretical bound. Further analysis shows that most algorithms have under-estimated the impact of spatio-temporal mismatches between the data from different sources, and the high sparsity of user generated data also contributes to the under-performance. Based on these insights, we propose four new algorithms that are specially designed to tolerate spatial or temporal mismatches (or both) and model location contexts and time contexts. Extensive evaluations show that our algorithms achieve more than 17 percent performance gain over the best existing algorithms, confirming our insights. Further, we propose two new location-privacy preserving mechanisms utilizing the spatio-temporal mismatches to better protect users' privacy against the de-anonymization attack. Evaluation results show that our proposed mechanisms can reduce the performance of de-anonymization attacks by over 8.0 percent, demonstrating the effectiveness of our insights.

In the modern information society, analysis of human mobility becomes increasingly essential in various areas such as city planning and resource management. With users' historical trajectories, the inherent patterns of their movements can be extracted and utilized to accurately predict the future movements. Plenty of previous work adopted traditional Markov model, which suffers when the trajectory becomes sparse or it shows distinct mobility patterns in different time of day. In this paper, based on an app-collected dataset of 100,000 individuals' actively uploaded location information, we comprehensively analyze the mobility and predictability of each user. To approach the theoretical predictability and overcome the shortcomings of traditional Markov model, we propose a time-variant Markov model based on Gibbs sampling for mobility prediction. Specifically, we model human mobility as several interconnected Markov chains, each chain corresponds to a movement pattern of a period of time. Then, we adopt Gibbs sampling method to simultaneously recover the missing part of trajectories and train the Markov chains, in order to solve the unevenly distribution and the high missing rate. Results show that our prediction algorithm can achieve 11.2 percent higher prediction accuracy than the benchmark method, especially on sparse trajectories. In addition, we discover a high correlation between prediction accuracy and predictability, with correlation coefficient reaching 0.81. Finally, we investigate various factors including spatial and temporal resolution, orders of Markov models, and radius of gyration, in order to further explore the predictability under different circumstances.

With the flourishing of location based social networks, posting check-ins has become a common practice to document one's daily life. Users usually do not consider check-in records as violations of their privacy. However, through analyzing two real-world check-in datasets, our study shows that check-in records are vulnerable to linkage attacks. Specifically, adversary is able to uniquely re-identify over 52~66 percent users in other anonymous mobility datasets and 60~80 percent users have more than 60 percent probability leaking unreported mobility records. In addition, we further demonstrate that the privacy sensitivity of check-in records can be more accurately measured by including the information of additional mobility data compared with only looking at check-ins. Based on this observation, we design a partition-and-group framework to integrate the information of check-ins and additional mobility data to attain a novel privacy criterion-kτ,l-anonymity. It ensures adversaries with arbitrary background knowledge cannot use check-ins to re-identify users in other anonymous datasets or learning unreported mobility records. The proposed framework achieves favorable performance against state-of-art baseline in terms of improving check-in utility by 24~57 percent while providing stronger privacy guarantee at the same time. We believe this study will open a new angle in attaining both privacy-preserving and useful check-in services.services.

Due to explosive growth of mobile data over the overburdened cellular network, opportunistic offloading is proposed to transmit the traffic originally transmitted through infrastructure network to delay-tolerant device-to-device networks at the edge of mobile networks. Existing offloading schemes mainly focus on selecting a subset of mobile nodes to work as offloadees, who first download the contents through the infrastructure, and then transmit them to subscriber nodes. However, when there is large amount of contents to be offloaded, and if all contents are disseminated through only one fixed set of offloadees every time, it may result in the risk of extreme cases that only extremely few nodes received the content, even if the expectation is large. This is like putting all of your eggs in one basket. To deal with this problem, we introduce an economic concept, conditional value at risk (CVaR) to measure the risk in offloadee set selection. CVaR is a widely used risk assessment measure for investments, which provides a unified and comprehensive risk evaluation framework for complex investment portfolio. We propose an algorithm to compute a portfolio over multiple offloadee sets with a guarantee on CVaR. Moreover, we prove the feasibility of our methodology from the mathematical point of view. Extensive evaluations with real-world traces show that our proposed offloading scheme can obtain a portfolio with significantly better CVaR, i.e., 91.53 percent performance gain at most, compared with the state-of-the-art solutions.

In-app advertising is a multi-billion dollar industry that is an essential part of the current digital ecosystem, and is amenable to sensitive consumer information often being sold downstream without the knowledge of consumers, and in many cases to their annoyance. While this practice, in cases, may result in long-term benefits for the consumers, it can result in serious information privacy (IP) breaches of very significant impact (e.g., breach of genetic data) in the short term. The question we raise through this article is: does the type of information being traded downstream play a role in the degree of IP risks generated? We investigate two general (one-many) information trading market structures between a single data aggregating seller (e.g., enterprise app) and multiple competing buyers (e.g., ad-networks, retailers), distinguished by mutually exclusive and privacy sanitized aggregated consumer data (information) types: (i) data entailing strategically complementary actions among buyers and (ii) data entailing strategically substituting actions among buyers. Our primary question of interest here is: trading which type of data might pose less information privacy risks for society? To this end, we show that at market equilibrium IP trading markets exhibiting strategic substitutes between buying firms pose lesser risks for IP in society, primarily because the `substitutes' setting, in contrast to the `complements' setting, economically incentivizes appropriate consumer data distortion by the seller in addition to restricting the proportion of buyers to which it sells. Moreover, we also show that irrespective of the data type traded by the seller, the likelihood of improved IP in society is higher if there is purposeful or free-riding based transfer/leakage of data between buying firms. This is because the seller finds itself economically incentivized to restrict the release of sanitized consumer data with respect to the span of its buyer space, as well as in improved data quality.

The emergence of Network Function Virtualization (NFV) and Software Defined Network (SDN) has greatly reformed the network. It is important to reduce the queuing delay spent/observed in NFV servers for the placement of Virtual Network Functions (VNFs). In this work, we mainly focus on the placement of VNFs with Poisson Arrived Traffic (VNFPPAT) to tackle the queuing delay problem. Both the Poisson distribution of traffic flows and various resource-sharing VNFs lead to the prolonged queuing delay in NFV servers with limited processing capacities. Considering the end-to-end delay as our optimization objective, we formulate this problem as a 0-1 quadratic fractional programming problem. This formulation is linearized to obtain the optimal solution for small scale networks. After proving VNFPPAT is NP-hard, we propose heuristic algorithms to obtain sub-optimal placement schemes. Through extensive simulations, we have shown that our proposed algorithms outperform the related state-of-the-art Improve Service Chaining Performance (ISCP) by 72% in terms of the end-to-end delay.

Today’s video streaming market is crowded with various content providers (CPs). For individual CPs, understanding user behavior, in particular how users migrate among different CPs, is crucial for improving users’ on-site experience and the CP’s chance of success. In this article, we take a data-driven approach to analyze and model user migration behavior in video streaming, i.e., users switching content provider during active sessions. Based on a large ISP dataset over two months (6 major content providers, 3.8 million users, and 315 million video requests), we study common migration patterns and reasons of migration. We find that migratory behavior is prevalent: 66% of users switch CPs with an average switching frequency of 13%. In addition, migration behaviors are highly diverse: regardless large or small CPs, they all have dedicated groups of users who like to switch to them for certain types of videos. Regarding reasons of migration, we find CP service quality rarely causes migration, while a few popular videos play a bigger role. Nearly 60% of cross-site migrations are landed to 0.14% top videos. Finally, we validate our findings by building an accurate regression model to predict user migration frequency as well as user survey, and discuss the implications of our results to CPs.

With the rapid growth of mobile networks and smart devices, a large number of people prefer to visiting video services via mobile devices. This generates massive data traffic, and thus increases the load of cellular networks. To deal with it, we need to investigate the usage patterns in the video consumption. In this article, we take a data-driven analysis of mobile video services by classifying them into three major types: traditional video portals, user-generated video services and personalized livestreaming. We collect a large dataset of 25,937,758 logs from 455 thousand users, and we find that 1) for the same kind of video services, users exhibit high loyalty; 2) in consecutive days, the traffic peaks have differences among different service types; 3) more video traffic is generated from personalized livestreaming services, and it keeps increasing after midnight at weekdays in the downtown; 4) traffic consumption of user-generated service exhibits great differences under different functional regions; 5) individual users are prone to click within the same service type but possible different time gaps during the consecutive views. Lastly, we utilize these findings to discuss the potential applications in the improvements of cellular networks and video services.

Cloud-Assisted Wireless Body Area Networks (WBANs) is one of the key emerging technology for medical applications in the era of Internet-of-Things. In cloud-assisted WBANs, the WBANs are able to access the cloud resources, which are geographically close to the local Access Points (APs). However, in the presence of poor radio link-quality between cloud-assisted WBANs and APs, energy consumption and service delay of the network dynamically changed. Therefore, in order to solve this problem, we propose an energy-efficient Body-to-Body (B2B) communications among coexisting WBANs to relay the information of the patients to nearest APs to provide real-time healthcare services. On the other hand, the healthcare services enabled for cloud-assisted WBANs is popularly known as Healthcare-as-a-Service (He-aaS). In He-aaS, it is very challenging to finalize a price agreement between WBANs and Health-Cloud Service Providers (H-CSPs) as WBANs follow a heterogeneous architecture. The existing pricing mechanisms, which are constrained to the homogeneous applications, are not compatible to He-aaS. We propose an optimal and distributed pricing policy for He-aaS in order to increase the profit level of each WBAN with the consideration of the optimal QoS and energy. Analysis of the proposed algorithms and the inferences of the results validates the usefulness of the proposed energy-efficient B2B communication and distributed pricing policy. Extensive results indicate that our proposed schemes are able to efficiently utilize limited resource with optimal QoS and energy consideration.

Mobile edge computing (MEC) has emerged as a new paradigm to assist low latency services by enabling computation offloading at the network edge. Nevertheless, human mobility can significantly impact the offloading decision and performance in MEC networks. In this context, we propose device-to-device (D2D) cooperation based MEC to expedite the task execution of mobile user by leveraging proximity-aware task offloading. However, user mobility in such distributed architecture results in dynamic offloading decision that instigates mobility-aware task scheduling in our proposed framework. We jointly formulate task assignment and power allocation to minimize the total task execution latency by taking account of user mobility, distributed resources, tasks properties, and energy constraint of the user device. We first propose Genetic Algorithm (GA)-based evolutionary scheme to solve our formulated mixed-integer non-linear programming (MINLP) problem. Then we propose a heuristic named mobility-aware task scheduling (MATS) to obtain effective task assignment with low complexity. The extensive evaluation under realistic human mobility trajectories provides useful insights into the performance of our schemes and demonstrates that, both GA and MATS achieve better latency than other baseline schemes while satisfying the energy constraint of mobile device.

In the past decade, the heterogeneous information network (HIN) has become an important methodology for modern recommender systems. To fully leverage its power, manually designed network templates, i.e., meta-structures, are introduced to filter out semantic-aware information. The hand-crafted meta-structure rely on intense expert knowledge, which is both laborious and data-dependent. On the other hand, the number of meta-structures grows exponentially with its size and the number of node types, which prohibits brute-force search. To address these challenges, we propose Genetic Meta-Structure Search (GEMS) to automatically optimize meta-structure designs for recommendation on HINs. Specifically, GEMS adopts a parallel genetic algorithm to search meaningful meta-structures for recommendation, and designs dedicated rules and a meta-structure predictor to efficiently explore the search space. Finally, we propose an attention based multi-view graph convolutional network module to dynamically fuse information from different meta-structures. Extensive experiments on three real-world datasets suggest the effectiveness of GEMS, which consistently outperforms all baseline methods in HIN recommendation. Compared with simplified GEMS which utilizes hand-crafted meta-paths, GEMS achieves over 6% performance gain on most evaluation metrics. More importantly, we conduct an in-depth analysis on the identified meta-structures, which sheds light on the HIN based recommender system design.

Online ad targeting can be formulated as a problem of learning the relevance ranking among possible audiences for a given ad. It has to deal with the massive number of negative,i.e., non-interacted, instances in impression data due to the nature of this service, and thus suffers from data imbalance problem. In this work, we tackle this problem by improving the quality of negative instances used in training the targeting model. We propose to enhance the generalization capability by introducing unobserved data as possible negative instances, and extract more reliable negative instances from the observed negatives in impression data. However, this idea is non-trivial to implement because of the limited learning signal and existing noise signal. To this end, we design a novel RNIG method (short for Representative Negative Instance Generator) to leverage feature matching technique. It aims to generate reliable negative instances that are similar to the observed negatives and further improves the representativeness of generated negatives by matching the most important feature. Extensive experiments on the real-world ad targeting dataset show that our RNIG model has achieved a relative improvement of more than 5%.

Predicting Origin-Destination (OD) flow is a crucial problem for intelligent transportation. However, it is extremely challenging because of three reasons: first, correlations exist between both origins and destinations; second, the correlations are dynamic across the time; at last, there are multiple correlations from different aspects. To the best of our knowledge, existing models for OD flow prediction cannot tackle all of these three issues simultaneously. We propose Multi-Perspective Graph Convolutional Networks (MPGCN) to capture the complex dependencies. Our proposed model first utilizes long short-term memory (LSTM) network to extract temporal features for each OD pair and then learns the spatial dependency of origins and destinations by a two-dimensional graph convolutional network. Furthermore, we design a dynamic graph together with two static graphs to capture the complicated spatial dependencies and use an average strategy to obtain the final predicted OD flow. We conduct extensive experiments on two large-scale and real-world datasets, which not only demonstrate our design philosophy but also validate the effectiveness of the proposed model.

In recent years, much research effort on recommendation has been devoted to mining user behaviors, i.e., collaborative filtering, along with the general information which describes users or items, e.g., textual attributes, categorical demographics, product images, and so on. Price, an important factor in marketing - which determines whether a user will make the final purchase decision on an item - surprisingly, has received relatively little scrutiny. In this work, we aim at developing an effective method to predict user purchase intention with the focus on the price factor in recommender systems. The main difficulties are twofold: 1) the preference and sensitivity of a user on item price are unknown, which are only implicitly reflected in the items that the user has purchased, and 2) how the item price affects a user's intention depends largely on the product category, that is, the perception and affordability of a user on item price could vary significantly across categories. Towards the first difficulty, we propose to model the transitive relationship between user-to-item and item-to-price, taking the inspiration from the recently developed Graph Convolution Networks (GCN). The key idea is to propagate the influence of price on users with items as the bridge, so as to make the learned user representations be price-aware. For the second difficulty, we further integrate item categories into the propagation progress and model the possible pairwise interactions for predicting user-item interactions. We conduct extensive experiments on two real-world datasets, demonstrating the effectiveness of our GCN-based method in learning the price-aware preference of users. Further analysis reveals that modeling the price awareness is particularly useful for predicting user preference on items of unexplored categories.

The increasing amount of urban data enable us to investigate urban dynamics, assist urban planning, and eventually, make our cities more livable and sustainable. In this paper, we focus on learning an embedding space from urban data for urban regions. For the first time, we propose a multi-view joint learning model to learn comprehensive and representative urban region embeddings. We first model different types of region correlations based on both human mobility and inherent region properties. Then, we apply a graph attention mechanism in learning region representations from each view of the built correlations. Moreover, we introduce a joint learning module that boosts the region embedding learning by sharing cross-view information and fuses multi-view embeddings by learning adaptive weights. Finally, we exploit the learned embeddings in the downstream applications of land usage classification and crime prediction in urban areas with real-world data. Extensive experiment results demonstrate that by exploiting our proposed joint learning model, the performance is improved by a large margin on both tasks compared with the state-of-the-art methods.

Population flow prediction is one of the most fundamental components in many applications from urban management to transportation schedule. It is challenging due to the complicated spatial-temporal correlation.While many studies have been done in recent years, they fail to simultaneously and effectively model the spatial correlation and temporal variations among population flows. In this paper, we propose Convolution based Sequential and Cross Network (CSCNet) to solve them. On the one hand, we design a CNN based sequential structure with progressively merging the flow features from different time in different CNN layers to model the spatial-temporal information simultaneously. On the other hand, we make use of the transition flow as the proxy to efficiently and explicitly capture the dynamic correlation between different types of population flows. Extensive experiments on 4 datasets demonstrate that CSCNet outperforms the state-of-the-art baselines by reducing the prediction error around 7.7%∼10.4%.

Realistic simulation of a massive amount of human mobility data is of great use in epidemic spreading modeling and related health policy-making. Existing solutions for mobility simulation can be classified into two categories: model-based methods and model-free methods, which are both limited in generating high-quality mobility data due to the complicated transitions and complex regularities in human mobility. To solve this problem, we propose a model-free generative adversarial framework, which effectively integrates the domain knowledge of human mobility regularity utilized in the model-based methods. In the proposed framework, we design a novel self-attention based sequential modeling network as the generator to capture the complicated temporal transitions in human mobility. To augment the learning power of the generator with the advantages of model-based methods, we design an attention-based region network to introduce the prior knowledge of urban structure to generate a meaningful trajectory. As for the discriminator, we design a mobility regularity-aware loss to distinguish the generated trajectory. Finally, we utilize the mobility regularities of spatial continuity and temporal periodicity to pre-train the generator and discriminator to further accelerate the learning procedure. Extensive experiments on two real-life mobility datasets demonstrate that our framework outperforms seven state-of-the-art baselines significantly in terms of improving the quality of simulated mobility data by 35%. Furthermore, in the simulated spreading of COVID-19, synthetic data from our framework reduces MAPE from 5% ~ 10% (baseline performance) to 2%.

Facing the worldwide rapid spreading of COVID-19 pandemic, we need to understand its diffusion in the urban environments with heterogeneous population distribution and mobility. However, challenges exist in the choice of proper spatial resolution, integration of mobility data into epidemic modelling, as well as incorporation of unique characteristics of COVID-19.

The tutorial focuses on two major themes of recent advances in recommender systems: Part A: Recommendations in a Marketplace: Multi-sided marketplaces are steadily emerging as valuable ecosystems in many applications (e.g. Amazon, AirBnb, Uber), wherein the platforms have customers not only on the demand side (e.g. users), but also on the supply side (e.g. retailer). This tutorial focuses on designing search & recommendation frameworks that power such multi-stakeholder platforms. We discuss multi-objective ranking/recommendation techniques, discuss different ways in which stakeholders specify their objectives, highlight user specific characteristics (e.g. user receptivity) which could be leveraged when developing joint optimization modules and finally present a number of real world case-studies of such multi-stakeholder platforms.

We study the problem of predicting regional economy of U.S. counties with open migration data collected from U.S. Internal Revenue Service (IRS) records. To capture the complicated correlations between them, we design a novel Attentional Multi-graph Convolutional Network (AMCN), which models the migration behavior as a multi-graph with different types of edges denoting the migration flows collected from heterogeneous sources of different years and different demographics. AMCN extracts high quality feature from the migration multi-graph by first applying customized aggregator functions on the induced subgraphs, and then fusing the aggregated features with a higher-order attentional aggregator function. In addition, we address the data sparsity problem with an important neighbor discovery algorithm that can automatically supplement important neighbors that are absent in the empirical data. Experiment results show our AMCN model significantly outperforms all baselines in terms of reducing the relative mean square error by 43.8% against the classic regression model and by 12.7% against the state-of-the-art deep learning baselines. In-depth model analysis shows our proposed AMCN model reveals insightful correlations between regional economy and migration data.

Negative sampling approaches are prevalent in implicit collaborative filtering for obtaining negative labels from massive unlabeled data. As two major concerns in negative sampling, efficiency and effectiveness are still not fully achieved by recent works that use complicate structures and overlook risk of false negative instances. In this paper, we first provide a novel understanding of negative instances by empirically observing that only a few instances are potentially important for model learning, and false negatives tend to have stable predictions over many training iterations. Above findings motivate us to simplify the model by sampling from designed memory that only stores a few important candidates and, more importantly, tackle the untouched false negative problem by favouring high-variance samples stored in memory, which achieves efficient sampling of true negatives with high-quality. Empirical results on two synthetic datasets and three real-world datasets demonstrate both robustness and superiorities of our negative sampling method. The implementation is available at https://github.com/dingjingtao/SRNS.

Bundle recommendation aims to recommend a bundle of items for a user to consume as a whole. Existing solutions integrate user-item interaction modeling into bundle recommendation by sharing model parameters or learning in a multi-task manner, which cannot explicitly model the affiliation between items and bundles, and fail to explore the decision-making when a user chooses bundles. In this work, we propose a graph neural network model named BGCN (short forBundle Graph Convolutional Network ) for bundle recommendation. BGCN unifies user-item interaction, user-bundle interaction and bundle-item affiliation into a heterogeneous graph. With item nodes as the bridge, graph convolutional propagation between user and bundle nodes makes the learned representations capture the item level semantics. Through training based on hard-negative sampler, the user's fine-grained preferences for similar bundles are further distinguished. Empirical results on two real-world datasets demonstrate the strong performance gains of BGCN, which outperforms the state-of-the-art baselines by 10.77% to 23.18%.

Most existing recommender systems leverage users' complete original behavioral logs, which are collected from mobile devices and stored by the service provider and further fed into recommendation models. This may lead to a high risk of privacy leakage since the recommendation service provider may be trustless. Despite many research efforts on privacy-aware recommendation, the problem of building an effective recommender system completely preserving user privacy is still open.

Traditional recommendation models that usually utilize only one type of user-item interaction are faced with serious data sparsity or cold start issues. Multi-behavior recommendation taking use of multiple types of user-item interactions, such as clicks and favorites, can serve as an effective solution. Early efforts towards multi-behavior recommendation fail to capture behaviors' different influence strength on target behavior. They also ignore behaviors' semantics which is implied in multi-behavior data. Both of these two limitations make the data not fully exploited for improving the recommendation performance on the target behavior.

With the rapid development of knowledge bases (KBs), link prediction task, which completes KBs with missing facts, has been broadly studied in especially binary relational KBs (a.k.a knowledge graph) with powerful tensor decomposition related methods. However, the ubiquitous n-ary relational KBs with higher-arity relational facts are paid less attention, in which existing translation based and neural network based approaches have weak expressiveness and high complexity in modeling various relations. Tensor decomposition has not been considered for n-ary relational KBs, while directly extending tensor decomposition related methods of binary relational KBs to the n-ary case does not yield satisfactory results due to exponential model complexity and their strong assumptions on binary relations. To generalize tensor decomposition for n-ary relational KBs, in this work, we propose GETD, a generalized model based on Tucker decomposition and Tensor Ring decomposition. The existing negative sampling technique is also generalized to the n-ary case for GETD. In addition, we theoretically prove that GETD is fully expressive to completely represent any KBs. Extensive evaluations on two representative n-ary relational KB datasets demonstrate the superior performance of GETD, significantly improving the state-of-the-art methods by over 15%. Moreover, GETD further obtains the state-of-the-art results on the benchmark binary relational KB datasets.

The prevalence of smartphones has promoted the popularity of mobile apps in recent years. Although significant effort has been made to understand mobile app usage, existing studies are based primarily on short-term datasets with limited time span, e.g., a few months. Therefore, many basic facts about the long-term evolution of mobile app usage are unknown. In this paper, we study how mobile app usage evolves over a long-term period. We first introduce an app usage collection platform named carat, from which we have gathered app usage records of 1,465 users from 2012 to 2017. We then conduct the first study on the long-term evolution processes on a macro-level, i.e., app-category, and micro-level, i.e., individual app. We discover that, on both levels, there is a growth stage enabled by the introduction of new technologies. Then there is a plateau stage caused by high correlations between app categories and a pareto effect in individual app usage, respectively. Additionally, the evolution of individual app usage undergoes an elimination stage due to fierce intra-category competition. Nevertheless, the diverseness of app-category and individual app usage exhibit opposing trends: app-category usage assimilates while individual app usage diversifies. Our study provides useful implications for app developers, market intermediaries, and service providers.

In collaborative filtering (CF), interaction function (IFC) play the important role of capturing interactions among items and users. The most popular IFC is the inner product, which has been successfully used in low-rank matrix factorization. However, interactions in real-world applications can be highly complex. Thus, other operations (such as plus and concatenation), which may potentially offer better performance, have been proposed. Nevertheless, it is still hard for existing IFCs to have consistently good performance across different application scenarios. Motivated by the recent success of automated machine learning (AutoML), we propose in this paper the search for simple neural interaction functions (SIF) in CF. By examining and generalizing existing CF approaches, an expressive SIF search space is designed and represented as a structured multi-layer perceptron. We propose an one-shot search algorithm that simultaneously updates both the architecture and learning parameters. Experimental results demonstrate that the proposed method can be much more efficient than popular AutoML approaches, can obtain much better prediction performance than state-of-the-art CF approaches, and can discover distinct IFCs for different data sets and tasks.1

Vehicular mobile crowdsensing (MCS) enables many smart city applications. Ridesharing vehicle fleets provide promising solutions to MCS due to the advantages of low cost, easy maintenance, high mobility, and long operational time. However, as nondedicated mobile sensing platforms, the first priorities of these vehicles are delivering passengers, which may lead to poor sensing coverage quality. Therefore, to help MCS derive good (large and balanced) sensing coverage quality, an actuation system is required to dispatch vehicles with a limited amount of monetary budget. This article presents PAS, a prediction-based actuation system for city-wide ridesharing vehicular MCS to achieve optimal sensing coverage quality with a limited budget. In PAS, two prediction models forecast probabilities of potential near-future vehicle routes and ride requests across the city. Based on prediction results, a prediction-based actuation planning algorithm is proposed to decide which vehicles to actuate and the corresponding routes. Experiments on city-scale deployments and physical feature-based simulations show that our PAS achieves up to 40% more improvement in sensing coverage quality and up to 20% higher ride request matching rate than baselines. In addition, to achieve a similar level of sensing coverage quality as the baseline, our PAS only needs 10% budget.

The explosive growth of traffic-consumption by mobile devices is leading to severe cellular network congestion, which is posing challenges for Internet Service Providers (ISPs) to provide good quality services with limited cellular capacity and impacting the user's experience. Data pricing has been proven to be an effective way to enhance both the service quality and ISP's profit. However, traditional data pricing schemes do not consider the real Mobile Application (App) Usage Patterns (MAUPs) among large scale cellular networks. In this paper, MAUPs aware smart data pricing scheme is proposed. In our work, we firstly extract and model the users' app usage behaviors of approximately 9,600 cellular towers as two-dimensional MAUPs (time, app category). Then 7 distinct derived MAUPs are considered to be incorporated into the user satisfaction model and ISP's profit model. The performance of our proposal is evaluated and verified by numerical experiments from the aspects of ISP's profit, consumption surplus, capacity utilization and traffic efficiency. The MAUPs based pricing scheme can be periodically updated according to the operational conditions and therefore significantly instructive for ISPs.

Social e-commerce, as a new form of social computing based marketing platforms, utilizes existing real-world social relationships for promotions and sales of products. It has been growing rapidly in recent years and attracted tens of millions of users in China. A key group of actors who enable market transactions on these platforms are intermediaries who connect producers with consumers by sharing information with and recommending products to their real-world social contacts. Despite their crucial role, the nature and behavior of these intermediaries on these social e-commerce platforms has not been systematically analyzed. Here we address this knowledge gap through a mixed method study. Leveraging 9 months' all-round behavior of about 40 million users on Beidian -- one of the largest social e-commerce sites in China, alongside with qualitative evidence from online forums and interviews, we examine characteristics of intermediaries, identify their behavioral patterns and uncover strategies and mechanisms that make successful intermediaries. We demonstrate that intermediaries on social e-commerce sites act as local trend detectors and "social grocers''. Furthermore, successful intermediaries are highly dedicated whenever best sellers appear and broaden items for promotion. To the best of our knowledge, this paper presents the first large-scale analysis on the emerging role of intermediaries in social e-commerce platforms, which provides potential insights for the design and management of social computing marketing platforms.

Understanding and characterizing the connectivity of vehicular networks has become increasingly important because of their wide applications and fast development. To address the dynamical links in vehicular networks, time-varying graph (TVG) is one of the most important models. Nowadays, due to the fact that lots of vehicular applications can tolerate a small amount of latency in communication, opportunistic reachability graph (ORG) characterizes the connectivity better by introducing delay tolerance to the model. However, people still do not have a high-level summarization, i.e., the topology, of the vehicular network on how nodes are clustered and isolated. In this paper, based on ORG model, we analyze the opportunistic topology of taxi networks in urban mobility environment by mainly focusing on the number, location and evolution of connected components and the size of the largest components to reveal the unique properties of the taxi networks instead of just links and hops. Our analysis is based on the real taxi traces of big cities and reflects the real urban mobility environment. We find that the opportunistic topology of the networks with delay tolerance is substantially different from the instantaneous topology without considering the delay. Moreover, we unveil the fundamental relationships and trade-offs between the dynamical topology and the key network parameters related to mobility, e.g., delay tolerance, transmission distance, etc. To the best of our knowledge, our study is the first work to reveal the characteristics of opportunistic topology models in the large-scale urban mobility environment with real traces.

Dynamic adaptive video streaming over hypertext transfer protocol (DASH) plays a key role in video transmission over the Internet. The conventional DASH adaptation approaches mainly focus on optimizing the overall quality of experience (QoE) for all client sides, neglecting the QoE diversity of different users. In this paper, we propose a meta-learning framework for multi-user preferences (MLMP) as a new DASH adaptation approach, which is able to optimize the diverse QoE of different users. Specifically, we first design a subjective experiment to analyze the difference of QoE preferences across users, in which QoE refers to the metrics of visual quality, fluctuation, and rebuffering events. Based on our findings, we formulate the QoE optimization of multi-user preferences as a multi-task deep reinforcement learning (DRL) problem. In our formulation, the QoE preference of each user is modeled in the overall QoE calculation via assigning the weights to the three QoE metrics. Then, the MLMP framework is developed to solve the proposed multi-task DRL problem, such that the preferences regarding visual quality, fluctuation, and rebuffering events can be optimized for different users in DASH adaptation. Finally, the simulation results show that the proposed approach outperforms state-of-the-art DASH adaptation approaches in satisfying the different users' QoE preferences regarding visual quality, fluctuation, and rebuffering events.

Smartphone mobile application (App) usage prediction, i.e., which Apps will be used next, is beneficial for user experience improvement. Through an in-depth analysis on a real-world dataset, we find that App usage is highly spatio-temporally correlated and personalized. Given the ability to model complex spatio-temporal contexts, we aim to apply deep learning to achieve high prediction accuracy. However, the personalization yields a problem: training one network for each individual suffers from data scarcity, yet training one deep neural network for all users often fails to uncover user preference. In this article, we propose a novel App usage prediction framework, named DeepApp , to achieve context-aware prediction via multi-task learning. To tackle the challenge of data scarcity, we train one general network for multiple users to share common patterns. To better utilize the spatio-temporal contexts, we supplement a location prediction task in the multi-task learning framework to learn spatio-temporal relations. As for the personalization, we add a user identification task to capture user preference. We evaluate DeepApp on the large-scale dataset by extensive experiments. Results demonstrate that DeepApp outperforms the start-of-the-art baseline by 6.44%.

Epilepsy is a chronic neurological disorder characterized by the occurrence of spontaneous seizures, which affects about one percent of the worlds population. Most of the current seizure detection approaches strongly rely on patient history records and thus fail in the patient-independent situation of detecting the new patients. To overcome such limitation, we propose a robust and explainable epileptic seizure detection model that effectively learns from seizure states while eliminates the inter-patient noises. A complex deep neural network model is proposed to learn the pure seizure-specific representation from the raw non-invasive electroencephalography (EEG) signals through adversarial training. Furthermore, to enhance the explainability, we develop an attention mechanism to automatically learn the importance of each EEG channels in the seizure diagnosis procedure. The proposed approach is evaluated over the Temple University Hospital EEG (TUH EEG) database. The experimental results illustrate that our model outperforms the competitive state-of-the-art baselines with low latency. Moreover, the designed attention mechanism is demonstrated ables to provide fine-grained information for pathological analysis. We propose an effective and efficient patient-independent diagnosis approach of epileptic seizure based on raw EEG signals without manually feature engineering, which is a step toward the development of large-scale deployment for real-life use.

Recognizing representative living patterns in population is extremely valuable for urban planning and decision making. Thanks to the growing popularity of location-based applications and check-ins on social networking sites, Point of Interest (POI) of a location is quite often available in the trajectory data, which expresses user living semantics. However, adopting trajectory semantics for living pattern recognition is an open and challenging research problem due to three major technical challenges: effective feature representation, suitable granularity selection for habit unit, and reliable habit distance measurement. In this paper, we propose a representation learning based system named habit2vec to represent user trajectory semantics in vector space, which preserves the original user living habit information. We evaluated our proposed system on a large-scale real-world dataset provided by a popular social network operator including 123,803 users for 1.5 months in Beijing. The results justify the representation ability of our system in preserving user habit pattern, and demonstrate the effectiveness of clustering users with similar living patterns.

With the rapid development of mobile applications, mobile edge computing (MEC), which provides various cloud resources (e.g., computation and storage resources) closer to mobile and IoT devices for computation offloading, has been broadly studied in both academia and industry. However, due to the limited coverage of static edge servers, the traditional MEC technology performs badly in a nowadays environment. To adapt the diverse demands, in this paper, we propose a novel mobile edge mechanism with a vehicle-mounted edge (V-edge) deployed. Aiming at maximizing completed tasks of V-edge with sensitive deadline, the problem of joint path planning and resource allocation is formulated into a mixed integer nonlinear program (MINLP). By utilizing the piecewise linear approximation and linear relaxation, we transform the MINLP into a mixed integer linear program (MILP). To obtain the nearoptimal solution, we further develop a gap-adjusted branch & bound algorithm, also called GA-B&B algorithm. Moreover, we propose a low-complexity L-step lookahead branch scheme (referred to as L-step scheme) for efficient scheduling in large-scale scenarios. Extensive evaluations demonstrate the superior performance of the proposed scheme compared with the traditional static edge mechanism. Furthermore, the proposed L-step scheme achieves close performance to the near-optimal solution, and significantly improves the task completion percentage of state-of-the-art schemes by over 10 percent.

The diversity of personal interest and preference of mobile users results in a wide spectrum of mobile app usage, and it is important to predict such app preference in order to provide personalized services. However, currently available individual app usage data is very limited, which does not cover a large user base. In this paper, we demonstrate that it is possible to make personalized app usage estimation by learning user's app preference from the social media, i.e., public accessible tweets, which can also reflect user's interest and make up for the sparsity of app usage data. By proposing a novel generative model named IMCF+ to transfer user interest from rich tweet information to sparse app usage, we achieve personalized app recommendations via learning the interest's correlation between apps and tweets. Based on a real-world app usage and tweet dataset over a large population, we evaluate the performance of IMCF+ with a variety of scenarios and parameters. With only 10 percent training data, our IMCF+ approach achieves 82.5 percent hitrate in predicting the top ten apps. Moreover, IMCF+ outperforms the other six state-of-the-art algorithms by 4.7 percent and 10 percent in high sparsity case and user cold-start scenario, indicating the effectiveness of our method. All these results demonstrate that our technique can reliably learn user's interest from tweets to help solve the personalized app recommendation problem. Our study is the first step forward for transferring user's interest learned from social media to app preference, which paves the way for providing higher-quality personalized app recommendation and services for mobile users.

It is well-known that online services resort to various cookies to track users through users' online service identifiers (IDs) - in other words, when users access online services, various “fingerprints” are left behind in the cyberspace. As they roam around in the physical world while accessing online services via mobile devices, users also leave a series of “footprints” - i.e., hints about their physical locations - in the physical world. This poses a potent new threat to user privacy: one can potentially correlate the “fingerprints” left by the users in the cyberspace with “footprints” left in the physical world to infer and reveal leakage of user physical world privacy, such as frequent user locations or mobility trajectories in the physical world - we refer to this problem as user physical world privacy leakage via user cyberspace privacy leakage. In this paper we address the following fundamental question: what kind - and how much - of user physical world privacy might be leaked if we could get hold of such diverse network datasets even without any physical location information. In order to conduct an in-depth investigation of these questions, we utilize the network data collected via a DPI system at the routers within one of the largest Internet operator in Shanghai, China over a duration of one month. We decompose the fundamental question into the three problems: i) linkage of various online user IDs belonging to the same person via mobility pattern mining; ii) physical location classification via aggregate user mobility patterns over time; and iii) tracking user physical mobility. By developing novel and effective methods for solving each of these problems, we demonstrate that the question of user physical world privacy leakage via user cyberspace privacy leakage is not hypothetical, but indeed poses a real potent threat to user privacy.

Large scale cellular network accessing records are generated by mobile users on daily basis, which leave fine-grained footprints that have potential to compromise the privacy of user mobility. Abundant previous researches have demonstrated that simple anonymization has limited effect in preserving user's privacy due to prevalence of re-identification attacks. As a result, the mobile operators and application vendors usually turn to a more aggressive solution that is removing the identifier (ID) of each entry in the records. Cellular data sets owners believe that such procedure is sufficient for preserving user's privacy, since the attackers cannot directly put together the cellular records that belong to one individual, let alone recover user's identity. However, in this paper, we argue and prove that simply removing the IDs is not sufficient for preserving mobile users' privacy. We develop a mechanism that is able to extract the mobility patterns of users from cellular records and associate ID-removed records belonging to same individuals. Extensive experiments show that 70%~80% records of each user on average can be accurately recovered for two data sets collected from both mobile application and mobile operator side at the scale of several thousands to tens of thousands users. We find that the number of users released, the temporal and spatial granularity, and the speed of user movement are key factors that determine the privacy leakage in the ID-removed cellular data sets.

Most existing recommender systems leverage the primary feedback only, despite the fact that users also generate a large amount of auxiliary feedback. These feedback usually indicate different user preferences when comparing to the primary feedback directly used to optimize the system performance. For example, in E-commerce sites, view data is easily accessible, which provides a valuable yet weaker signal than the primary feedback of purchase. In this work, we improve implicit feedback-based recommender systems (dubbed Implicit Recommender Systems ) by integrating auxiliary view data into matrix factorization (MF). To exploit different preference levels, we propose both pointwise and pairwise models in terms of how to leverage users’ viewing behaviors. The latter model learns the pairwise ranking relations among purchased, viewed, and non-viewed interactions, being more effective and flexible than the former pointwise MF method. However, such a pairwise formulation poses a computational efficiency problem in learning the model. To address this problem, we design a new learning algorithm based on the element-wise Alternating Least Squares (eALS) learner. Notably, our designed algorithm can efficiently learn model parameters from the whole user-item matrix (including all missing data), with a rather low time complexity that is dependent on the observed data only. Extensive experiments on two real-world datasets demonstrate that our method outperforms several state-of-the-art MF methods by 6.43%∼ 6.75%. Our implementation is available at https://github.com/dingjingtao/Auxiliary_enhanced_ALS.

Because of severe network congestion experienced during peak hours in the urban area, dynamic time-dependent pricing has been proposed by some mobile operators to shift users' data usage from peak hours to off-peak time slots. We look at the performance of time-dependent pricing on a large scale cellular network comprising ten thousand base stations. Our investigation reveals two important observations. First, time-dependent pricing performs well in reducing the peak-average ratio of the overall traffic of the network. However, the single price used by the network does not achieve good performance when we look at base stations in specific regions, such as office regions. Second, we observe that location is another important factor that affects the traffic profile of a base station. Therefore, location information should be considered for designing a pricing strategy as well. We propose a framework that combines both spatial and temporal traffic patterns for data pricing. Our simulation on ten thousand base stations suggests that our proposed scheme is able to achieve an average of 16 percent smaller peak-to-average ratio. With over 15 percent smaller peak-to-average ratio of more than half of base stations in office regions, the performance is 2× better than that achieved by the state of the art time-dependent data pricing systems.

Combining Network Functions Virtualization (NFV) with Software-Defined Networking (SDN) is an emerging and promising solution to provide scalable and elastic network control and service. In such a system, virtualized Network Functions (NFs) need to be consistently migrated from one instance to another for various purposes, such as resource optimization, fault tolerance, load balancing, etc. These migrations involve simultaneously coordinating updates to the NF state and SDN forwarding state. To solve this problem, we design two consistent NF state update schemes: a controller-forwarding based scheme and a tagging-based scheme. Through analysis of the update process, we demonstrate that they both guarantee loss-free and order-preserving migrations. We further implement a prototype and carry out experiments with diverse traffic settings. Results demonstrate that the controller-forwarding based solution achieves 77 percent migration time compared with the state-of-the-art solution OpenNF, while correcting an error of it. Moreover, the tagging-based solution not only achieves 4.4 percent migration time, but also reduces up to 75 percent controller overhead compared with OpenNF at the cost of adding a tag in the unused fields of packet header.

Crowd flow prediction is of great importance in a wide range of applications from urban planning, traffic control to public safety. It aims to predict the inflow (the traffic of crowds entering a region in a given time interval) and outflow (the traffic of crowds leaving a region for other places) of each region in the city with knowing the historical flow data. In this paper, we propose DeepSTN+, a deep learning-based convolutional model, to predict crowd flows in the metropolis. First, DeepSTN+ employs the ConvPlus structure to model the longrange spatial dependence among crowd flows in different regions. Further, PoI distributions and time factor are combined to express the effect of location attributes to introduce prior knowledge of the crowd movements. Finally, we propose an effective fusion mechanism to stabilize the training process, which further improves the performance. Extensive experimental results based on two real-life datasets demonstrate the superiority of our model, i.e., DeepSTN+ reduces the error of the crowd flow prediction by approximately 8%∼13% compared with the state-of-the-art baselines.

Dynamic high resolution data on human population distribution is of great importance for a wide spectrum of activities and real-life applications, but is too difficult and expensive to obtain directly. Therefore, generating fine-scaled population distributions from coarse population data is of great significance. However, there are three major challenges: 1) the complexity in spatial relations between high and low resolution population; 2) the dependence of population distributions on other external information; 3) the difficulty in retrieving temporal distribution patterns. In this paper, we first propose the idea to generate dynamic population distributions in full-time series, then we design dynamic population mapping via deep neural network(DeepDPM), a model that describes both spatial and temporal patterns using coarse data and point of interest information. In DeepDPM, we utilize super-resolution convolutional neural network(SRCNN) based model to directly map coarse data into higher resolution data, and a timeembedded long short-term memory model to effectively capture the periodicity nature to smooth the finer-scaled results from the previous static SRCNN model. We perform extensive experiments on a real-life mobile dataset collected from Shanghai. Our results demonstrate that DeepDPM outperforms previous state-of-the-art methods and a suite of frequent data-mining approaches. Moreover, DeepDPM breaks through the limitation from previous works in time dimension so that dynamic predictions in all-day time slots can be obtained.

Recent years have witnessed a phenomenal success of agent-initiated social e-commerce models, which encourage users to become selling agents to promote items through their social connections. The complex interactions in this type of social e-commerce can be formulated as Heterogeneous Information Networks (HIN), where there are numerous types of relations between three types of nodes, i.e., users, selling agents and items. Learning high quality node embeddings is of key interest, and Graph Convolutional Networks (GCNs) have recently been established as the latest state-of-the-art methods in representation learning. However, prior GCN models have fundamental limitations in both modeling heterogeneous relations and efficiently sampling relevant receptive field from vast neighborhood. To address these problems, we propose RecoGCN, which stands for a RElation-aware CO-attentive GCN model, to effectively aggregate heterogeneous features in a HIN. It makes up current GCN's limitation in modelling heterogeneous relations with a relation-aware aggregator, and leverages the semantic-aware meta-paths to carve out concise and relevant receptive fields for each node. To effectively fuse the embeddings learned from different meta-paths, we further develop a co-attentive mechanism to dynamically assign importance weights to different meta-paths by attending the three-way interactions among users, selling agents and items. Extensive experiments on a real-world dataset demonstrate RecoGCN is able to learn meaningful node embeddings in HIN, and consistently outperforms baseline methods in recommendation tasks.

Increasingly available city data and advanced learning techniques have empowered people to improve the efficiency of our city functions. Among them, improving urban transportation efficiency is one of the most prominent topics. Recent studies have proposed to use reinforcement learning (RL) for traffic signal control. Different from traditional transportation approaches which rely heavily on prior knowledge, RL can learn directly from the feedback. However, without a careful model design, existing RL methods typically take a long time to converge and the learned models may fail to adapt to new scenarios. For example, a model trained well for morning traffic may not work for the afternoon traffic because the traffic flow could be reversed, resulting in very different state representation. In this paper, we propose a novel design called FRAP, which is based on the intuitive principle of phase competition in traffic signal control: when two traffic signals conflict, priority should be given to one with larger traffic movement (i.e., higher demand). Through the phase competition modeling, our model achieves invariance to symmetrical cases such as flipping and rotation in traffic flow. By conducting comprehensive experiments, we demonstrate that our model finds better solutions than existing RL methods in the complicated all-phase selection problem, converges much faster during training, and achieves superior generalizability for different road structures and traffic conditions.

Map matching is important in many trajectory based applications like route optimization and traffic schedule, etc. As the widely used methods, Hidden Markov Model and its variants are well studied to provide accurate and efficient map matching service. However, HMM based methods fail to utilize the value of enormous trajectory big data, which are useful for the map matching task. Furthermore, with many following-up works, they are still easily influenced by the noisy records, which are very common in the real system. To solve these problems, we revisit the map matching task from the data perspective, and propose to utilize the great power of data to help solve these problems. We build a deep learning based model to utilize all the trajectory data for joint training and knowledge sharing. With the help of embedding techniques and sequence learning model with attention enhancement, our system does the map matching in the latent space, which is tolerant to the noise in the physical space. Extensive experiments demonstrate that our model outperforms the widely used HMM based methods more than 10% (absolute accuracy) and works robustly in the noisy settings in the meantime.

Network Function Virtualization (NFV) and Software Defined Network have revolutionized data networks. For deployment of the VNFs, it is imperative to consider the queuing delay occurring in the NFV servers. The presented work suggests to incorporate the Poisson distribution of packet arrival rate and packet size along with the limited processing capacity of NFV server. The underlying phenomenon is framed as a 0-1 fractional programming problem. More precisely, the underlying problem is framed to 0-1 MILP to get the optimal solution. Since the VNF placement problem is NP-hard, therefore, we propose two heuristic algorithms to get the solution. Extensive simulations demonstrate that our algorithms effectively reduce 72.9% delay compared with the universal algorithm Improve Service Chaining Performance (ISCP).

Most existing recommender systems leverage user behavior data of one type, such as the purchase behavior data in E-commerce. We argue that other types of user behavior data also provide valuable signal, such as views, clicks, and so on. In this work, we contribute a new solution named NMTR (short for Neural Multi-Task Recommendation) for learning recommender systems from user multi-behavior data. In particular, our model accounts for the cascading relationship among different types of behaviors (e.g., a user must click on a product before purchasing it). We perform a joint optimization based on the multi-task learning framework, where the optimization on a behavior is treated as a task. Extensive experiments on the real-world dataset demonstrate that NMTR significantly outperforms state-of-the-art recommender systems that are designed to learn from both single-behavior data and multi-behavior data.

In implicit feedback-based recommender systems, user exposure data, which record whether or not a recommended item has been interacted by a user, provide an important clue on selecting negative training samples. In this work, we improve the negative sampler by integrating the exposure data. We propose to generate high-quality negative instances by adversarial training to favour the difficult instances, and by optimizing additional objective to favour the real negatives in exposure data. However, this idea is non-trivial to implement since the distribution of exposure data is latent and the item space is discrete. To this end, we design a novel RNS method (short for Reinforced Negative Sampler) that generates exposure-alike negative instances through feature matching technique instead of directly choosing from exposure data. Optimized under the reinforcement learning framework, RNS is able to integrate user preference signals in exposure data and hard negatives. Extensive experiments on two real-world datasets demonstrate the effectiveness and rationality of our RNS method. Our implementation is available at: https://github. com/dingjingtao/ReinforceNS.

Existing web video systems recommend videos according to users' viewing history from its own website. However, since many users watch videos in multiple websites, this approach fails to capture these users' interests across sites. In this paper, we investigate the user viewing behavior in multiple sites based on a large scale real dataset. We find that user interests are comprised of cross-site consistent part and site-specific part with different degrees of the importance. Existing linear matrix factorization recommendation model has limitation in modeling such complicated interactions. Thus, we propose a model of Deep Attentive Probabilistic Factorization (DeepAPF) to exploit deep learning method to approximate such complex user-video interaction. DeepAPF captures both cross-site common interests and site-specific interests with non-uniform importance weights learned by the attentional network. Extensive experiments show that our proposed model outperforms by 17.62%, 7.9% and 8.1% with the comparison of three state-of-the-art baselines. Our study provides insight to integrate user viewing records from multiple sites via the trusted third party, which gains mutual benefits in video recommendation.

Urban anomalies such as abnormal flow of crowds and traffic accidents could result in loss of life or property if not handled properly. Detecting urban anomalies at the early stage is important to minimize the adverse effects. However, urban anomaly detection is difficult due to two challenges: a) the criteria of urban anomalies varies with different locations and time; b) urban anomalies of different types may show different signs. In this paper, we propose a decomposing approach to address these two challenges. Specifically, we decompose urban dynamics into the normal component and the abnormal component. The normal component is merely decided by spatiotemporal features, while the abnormal component is caused by anomalous events. Then, we extract spatiotemporal features and estimate the normal component accordingly. At last, we derive the abnormal component to identify anomalies. We evaluate our method using both real-world and synthetic datasets. The results show our method can detect meaningful events and outperforms state-of-the-art anomaly detecting methods by a large margin.

As a comprehensive information carrier, the short video is gaining increasing attention for a user to spread information, read the news and conduct interpersonal communication. Consequently, short video recommendation problem has been a hot spot in the field of the recommender system. However, current short video recommendation algorithms have to tackle with data sparsity and cold start problem, which is caused by the small amounts of data that the recommender system has accumulated and massive video data while limited users' access.Aiming at the problem of data sparsity and cold start, the paper proposes a short video recommendation algorithm Social Weak-tie Bayesian Personalized Ranking (SWTBPR). Social weak-tie refers to the following relation in online social network, which means they are not real-world friends, somehow it can reflect users' preference. Experimental results demonstrate that SWTBPR outperforms other existing video recommendation algorithms and solves the data sparsity and cold start problem with a real-world dataset collected from Sina Weibo.

Recommendation models mainly deal with categorical variables, such as user/item ID and attributes. Besides the high-cardinality issue, the interactions among such categorical variables are usually long-tailed, with the head made up of highly frequent values and a long tail of rare ones. This phenomenon results in the data sparsity issue, making it essential to regularize the models to ensure generalization. The common practice is to employ grid search to manually tune regularization hyperparameters based on the validation data. However, it requires non-trivial efforts and large computation resources to search the whole candidate space; even so, it may not lead to the optimal choice, for which different parameters should have different regularization strengths. In this paper, we propose a hyperparameter optimization method, lambdaOpt, which automatically and adaptively enforces regularization during training. Specifically, it updates the regularization coefficients based on the performance of validation data. With lambdaOpt, the notorious tuning of regularization hyperparameters can be avoided; more importantly, it allows fine-grained regularization (i.e. each parameter can have an individualized regularization coefficient), leading to better generalized models. We show how to employ lambdaOpt on matrix factorization, a classical model that is representative of a large family of recommender models. Extensive experiments on two public benchmarks demonstrate the superiority of our method in boosting the performance of top-K recommendation.

Hidden Markov Model (HMM) is a powerful tool that has been widely adopted in sequence modeling tasks, such as mobility analysis, healthcare informatics, and online recommendation. However, using HMM for modeling personalized sequences remains a challenging problem: training a unified HMM with all the sequences often fails to uncover interesting personalized patterns; yet training one HMM for each individual inevitably suffers from data scarcity. We address this challenge by proposing a state-sharing sparse hidden Markov model (S3HMM) that can uncover personalized sequential patterns without suffering from data scarcity. This is achieved by two design principles: (1) all the HMMs in the ensemble share the same set of latent states; and (2) each HMM has its own transition matrix to model the personalized transitions. The result optimization problem for S3HMM becomes nontrivial, because of its two-layer hidden state design and the non-convexity in parameter estimation. We design a new Expectation-Maximization algorithm based, which treats the difference of convex programming as a sub-solver to optimize the non-convex function in the M-step with convergence guarantee. Our experimental results show that, S3HMM can successfully uncover personalized sequential patterns in various applications and outperforms baselines significantly in downstream prediction tasks.

We design a flexible data plane to integrate SDN and ENFV to manage complex network services for future mobile services. We build our prototype and show its feasibility in terms of latency and throughput by using mobile edge computing as an example use case in a realistic mobile networking testbed.

As a key UI feature of Android, overlay enables one app to draw over other apps by creating an extra View layer on top of the host View. While greatly facilitating user interactions with multiple apps at the same time, it is often exploited by malicious apps (malware) to attack users. To combat this threat, prior countermeasures concentrate on restricting the capabilities of overlays at the OS level, while barely seeing adoption by Android due to the concern of sacrificing overlays' usability. To address this dilemma, a more pragmatic approach is to enable the early detection of overlay-based malware at the app market level during the app review process, so that all the capabilities of overlays can stay unchanged. Unfortunately, little has been known about the feasibility and effectiveness of this approach for lack of understanding of malicious overlays in the wild. To fill this gap, in this paper we perform the first large-scale comparative study of overlay characteristics in benign and malicious apps using static and dynamic analyses. Our results reveal a set of suspicious overlay properties strongly correlated with the malice of apps, including several novel features. Guided by the study insights, we build OverlayChecker, a system that is able to automatically detect overlay-based malware at market scales. OverlayChecker has been adopted by one of the world's largest Android app stores to check around 10K newly submitted apps per day. It can efficiently (within 2 minutes per app) detect nearly all (96%) overlay-based malware using a single commodity server.

Edge computing paradigm aims at offloading microservices from mobile devices to the edge of network, reducing latency and increasing computational ability. Differently from the monolithic architecture, in a microservice-based system, an application is developed as a suite of microservices, each running independently on containers. To optimize the offloading decision, existing schemes often require a priori knowledge of the service type, latency-requirement, or both. Such limitations, in turn, hinders the quality-of-service (QoS) for real-time (mobile) applications. This paper presents FLAVOUR, a novel distributed and latency-optimal microservice scheduling mechanism for edge computing platform to achieve minimal service latency, while providing guaranteed transmission rates to minimize microservice completion times (MSCT). To design FLAVOUR, we first formulate a stochastic service delay minimization problem with constraints on MSCT and network stability. By solving this problem, we derive an optimal latency-optimal heuristic scheduling problem, which establishes the theoretical foundation for FLAVOUR. We have implemented a FLAVOUR prototype and evaluated FLAVOUR through both the testbed experiments and CloudSim simulations. Our preliminary results show that FLAVOUR holds great promise in terms of latency and throughput under different traffic dynamics.

Understanding human mobility benefits numerous applications such as urban planning, traffic control and city management. Previous work mainly focuses on modeling spatial and temporal patterns of human mobility. However, the semantics of trajectory are ignored, thus failing to model people's motivation behind mobility. In this paper, we propose a novel semantics-aware mobility model that captures human mobility motivation using large-scale semantics-rich spatial-temporal data from location-based social networks. In our system, we first develop a multimodal embedding method to project user, location, time, and activity on the same embedding space in an unsupervised way while preserving original trajectory semantics. Then, we use hidden Markov model to learn latent states and transitions between them in the embedding space, which is the location embedding vector, to jointly consider spatial, temporal, and user motivations. In order to tackle the sparsity of individual mobility data, we further propose a von Mises-Fisher mixture clustering for user grouping so as to learn a reliable and fine-grained model for groups of users sharing mobility similarity. We evaluate our proposed method on two large-scale real-world datasets, where we validate the ability of our method to produce high-quality mobility models. We also conduct extensive experiments on the specific task of location prediction. The results show that our model outperforms state-of-the-art mobility models with higher prediction accuracy and much higher efficiency.

Social e-commerce, as a new concept of e-commerce, uses social media as a new prevalent platform for online shopping. Users are now able to view, add to cart, and buy products within a single social media app. In this paper, we address the problem of cross-platform recommendation for social e-commerce, i.e., recommending products to users when they are shopping through social media. To the best of our knowledge, this is a new and important problem for all e-commerce companies (e.g. Amazon, Alibaba), but has never been studied before.

Online services are playing critical roles in almost all aspects of users' life. Users usually have multiple online identities (IDs) in different online services. In order to fuse the separated user data in multiple services for better business intelligence, it is critical for service providers to link online IDs belonging to the same user. On the other hand, the popularity of mobile networks and GPS-equipped smart devices have provided a generic way to link IDs, i.e., utilizing the mobility traces of IDs. However, linking IDs based on their mobility traces has been a challenging problem due to the highly heterogeneous, incomplete and noisy mobility data across services.

Web systems that provide the same functionality usually share a certain amount of items. This makes it possible to combine data from different websites to improve recommendation quality, known as the cross-domain recommendation task. Despite many research efforts on this task, the main drawback is that they largely assume the data of different systems can be fully shared. Such an assumption is unrealistic - different systems are typically operated by different companies, and it may violate business privacy policy to directly share user behavior data since it is highly sensitive.

Modeling people's activities in the urban space is a crucial socio-economic task but extremely challenging due to the deficiency of suitable methods. To model the temporal dynamics of human activities concisely and specifically, we present State-sharing Hidden Markov Model (SSHMM). First, it extracts the urban states from the whole city, which captures the volume of population flows as well as the frequency of each type of Point of Interests (PoIs) visited. Second, it characterizes the urban dynamics of each urban region as the state transition on the shared-states, which reveals distinct daily rhythms of urban activities. We evaluate our method via a large-scale real-life mobility dataset and results demonstrate that SSHMM learns semantics-rich urban dynamics, which are highly correlated with the functions of the region. Besides, it recovers the urban dynamics in different time slots with an error of 0.0793, which outperforms the general HMM by 54.2%.

With the flourishing of location based social networks, posting check-ins has become a common practice to document one's daily life. Users usually do not consider check-in records as violations of their privacy. However, through analyzing two real-world check-in datasets, our study shows that check-in records are vulnerable to linkage attacks. To address this problem, we design a partition-and-group framework to integrate the information of check-ins and additional mobility data to attain a novel privacy criterion - kt, l-anonymity. It ensures adversaries with arbitrary background knowledge cannot use check-ins to re-identify users in other anonymous datasets or learning unreported mobility records. The proposed framework achieves favorable performance against state-of-art baseline in terms of improving check-in utility by 24% ~ 57% while providing stronger privacy guarantee at the same time. We believe this study will open a new angle in attaining both privacy-preserving and useful check-in services.

| openaire: EC/H2020/815191/EU//PriMO-5G

Research in large-scale networking systems has been shaped and will continue to be guided by specific characteristics of applications and the underlying platforms and infrastructures. On the one hand, applications are growing at an accelerated pace, which is fundamentally unpredictable in both breadth and depth. On the other hand, the underlying networking has been the focus of a huge transformation enabled by new models resulting from virtualization and cloud computing. This has led to a number of novel architectures supported by emerging technologies such as Software-Defined Networking (SDN), Network Function Virtualization (NFV), and more recently, edge cloud and fog networking, or network slicing[1],[2]. This evolution towards enhanced design opportunities along with increasing complexity in networking and its applications has fueled the need for improved network automation in agile infrastructures. At the same time, their complexity has dramatically increased. The networking dynamics have had the effect of making it even more important and challenging to design scalable network measurement and analysis techniques and associated tools. Critical applications such as resource allocation, network monitoring, security enforcement, or dynamic network management require real-time mechanisms for online analysis as well as efficient techniques for offline deep analysis of massive historical data.

Understanding the roles of social factors in online purchase behavior has been a long standing research problem. The recently emerging social e-commerce platforms leverage the stimulated word-of-mouth effect to promote the sales of items, which offers a peek into the complex interplay between the social influence and online purchasing behavior. In this paper, we investigate this problem on a full-scale purchase behavior dataset from one of the leading social e-commerce platforms, Beidian. Specifically, we conduct a comparison study between the social e-commerce and conventional e-commerce that are both integrated in Beidian to examine how social factors affect user's purchase behavior. We reveal that social e-commerce leads to a 3.09~10.37 times higher purchase conversion rate compared with the conventional settings, which indicates users make purchase with significantly fewer item explorations. Then, we propose and validate four primary mechanisms that contribute to the efficient purchase conversion: better matching, social enrichment, social proof and price sensitivity. Moreover, we identify several behavioral indicators that are able to measure the effect of these mechanisms, based on which we design an accurate predictive model (AUC=0.7738) for user's purchase decision. These results combine to shed light on how to understand and model the purchase behavior in social e-commerce.

Understanding the patterns of mobile data consumption is extremely valuable to reveal human activities and ecology in urban areas. This task is nontrivial in terms of three challenges: the complexity of mobile data consumption in large urban environment, the disturbance of abnormal events, and lack of prior knowledge for urban traffic patterns. We propose a novel approach to design a powerful system that consists of three subsystems: time series decomposing of mobile traffic data, extracting patterns from different components of the original traffic, and detecting anomalous events from noises. Our investigation involving the mobile traffic records of 6,400 cellular towers in Shanghai reveals three important observations. First, among all the 6,400 cellular towers, we identify five daily patterns corresponding to different human daily activity patterns. Second, we find that two natural patterns can be extracted from the weekly trend of mobile traffic consumption, which reflects modes of human activities. Last but not least, besides the regular patterns, we investigate how irregular activities affect mobile traffic consumption, and exploit this knowledge to successfully detect unusual events like concerts and soccer matches. Our proposed methodology therefore will aid a comprehensive understanding of large-scale mobile traffic consumption in urban areas.

Accurate and comprehensive end-to-end network performance measurement is critical for the automatic troubleshooting and optimized provision of various services in Cloud. However, cloud providers and tenants still rely on rudimentary and separate tools for end-to-end performance measurement, which are inflexible, tedious, and error-prone. In this paper, we present NetWatch, a system that provides measurement as a service through open APIs for both cloud providers and tenants to measure end-to-end performance on-demand. In this system, measurement requests are first delivered to NetWatch Controller by open APIs, which transforms the request to configure specific Probes to fulfill the requests by active measurement. We make delicate design choices and address several challenges to enable NetWatch offering accurate and low-overhead measurement service for multiple users simultaneously and efficiently. A prototype implementation and experiments with diverse network settings link and traffic demonstrate that NetWatch can support flexible and accurate measurement of end-to-end network performance with small overhead.

Live migration is a key technique for virtual machine (VM) management in data center networks, which enables flexibility in resource optimization, fault tolerance, and load balancing. Despite its usefulness, the live migration still introduces performance degradations during the migration process. Thus, there has been continuous efforts in reducing the migration time in order to minimize the impact. From the network's perspective, the migration time is determined by the amount of data to be migrated and the available bandwidth used for such transfer. In this paper, we examine the problem of how to schedule the migrations and how to allocate network resources for migration when multiple VMs need to be migrated at the same time. We consider the problem in the Software-defined Network (SDN) context since it provides flexible control on routing. More specifically, we propose a method that computes the optimal migration sequence and network bandwidth used for each migration. We formulate this problem as a mixed integer programming, which is NP-hard. To make it computationally feasible for large scale data centers, we propose an approximation scheme via linear approximation plus fully polynomial time approximation, and obtain its theoretical performance bound and computational complexity. Through extensive simulations, we demonstrate that our fully polynomial time approximation (FPTA) algorithm has a good performance compared with the optimal solution of the primary programming problem and two state-of-the-art algorithms. That is, our proposed FPTA algorithm approaches to the optimal solution of the primary programming problem with less than 10 percent variation and much less computation time. Meanwhile, it reduces the total migration time and service downtime by up to 40 and 20 percent compared with the state-of-the-art algorithms, respectively.

Various dedicated web services in the cyberspace, e.g., social networks, e-commerce, and instant communications, play a significant role in people's daily-life. Billions of people around the world access these services through multiple online identifiers (IDs), and interact with each other in both the cyberspace and the physical world. Thanks to the rapid development of wireless and mobile technologies, nowadays these two kinds of interactions are highly relevant with each other. In order to link between the cyberspace and the physical world, we propose a new type of social network, i.e., co-location social network (CLSN). A CLSN contains online IDs describing people's online presence and offline “encountering” events when people come across each other. By analyzing real data collected from a mainstream ISP in China, which contains 32.7 million IDs across the most popular web services, we build a large-scale CLSN, and explore its unique properties from various aspects. The results indicate that the CLSN is quite different from existing online and offline social networks in terms of classic graph metrics. Moreover, we propose a community-based user identification algorithm to find all online IDs belonging to the same physical user. Using some ground-truth data, we demonstrate that our proposed algorithm achieves a high accuracy in user identification. Finally, we perform a user-centric analysis, and we demonstrate the behavioral difference among different types of users.

As the largest microblogging service in China, Sina Weibo, is associated with a huge amount of traffic to and from other major websites. Thanks to a massive set of anonymized data from a major operator covering a large-scale metropolitan area, we extract the click-based transitions between Weibo and other websites. Such transitions have not been looked into in most studies that rely on the visible hyper-links among websites. Based on this unique dataset, we show that 38% of the outgoing transitions (leaving Weibo) go to video clip services. Comparatively, links related to news and long videos are clicked less but posted more. This indicates that photograph and text-sharing in microblog have been gradually replaced by video clip sharing. Also, ignoring video clip sharing, 53% of the transitions go to five of the largest Chinese websites, showing how closely connected Weibo has become in the Chinese Web ecosystem. We further look at users' click behavior in transitions, and find that through co-clustering there do exist a number of prevalent and distinct behavior patterns, suggesting that only seven co-clusters can capture the click behavior of 192 000 studied users. Overall, our work is the first to unveil the significant role of microblogging platforms in the Web ecosystem. Considering the massive user base of Weibo, our findings can aid the design of more personalized link recommendation in Weibo, thus generating more referral traffic, i.e., user visits, from Weibo to other major websites.

Nowadays, human trajectories are widely collected and utilized for scientific research and business purpose. However, publishing trajectory data without proper handling might cause severe privacy leakage. A large body of works is dedicated to merging one’s trajectory with others’, so as to avoid any individual trajectory being re-identified. Yet their solutions do not provide enough protection since they cannot prevent semantic attack, which means the attackers are able to acquire individual’s private information by using the semantics features of frequently visited locations in the trajectory even without re-identification. In this paper, we are the first to recognize the semantic attack, which is another severe privacy problem in publishing trajectory datasets. We propose an algorithm providing strong privacy protection against both the semantic and re-identification attack while reserving high data utility. Extensive evaluations based on two real-world datasets demonstrate that our solution improves the quality of privacy protection by three times, sacrificing only 36% and 10% of spatial and temporal resolution, respectively.

With the rise of social networking and the awareness of privacy protection, the large-scale positioning data is getting harder to access while the clickstream data of social networking is accumulating. It is necessary to conduct a comprehensive study on the temporal property and spatial distribution of social network's clickstream to determine the latent relationship between clickstream and location semantics which semantically annotate locations to help us understand the purpose of a social network user at a certain location and a particular time. In this paper, we first infer the location semantics from Internet logs as our baseline which is a large scale, imprecise positioning mobile dataset through combining the utilization of derived time pattern and speed pattern. Then we design a method to reconstruct location semantics through the social network. We are the first to our knowledge that define “click motif” of social network's clickstream which is the combination of clicks in clickstream that occurs repeatedly and has significance. Click motif not only can help us to classify location semantics but also enhance the user experience of social networking. Besides, we propose a completed process to extract typical click motifs from a large-scale complicated clickstream data via embedding and clustering method. By extensive experiments and analysis, we demonstrate that different combination of click motifs can convey the users' location semantics, therefore clickstream may disclose location privacy.

Trajectory data has been widely collected via mobile devices and publicly released for academic research and commercial purposes. One primary concern of publishing such a dataset is the privacy issue. Previous protection schemes mainly focus on preventing re-identification attack, which utilizes the uniqueness of trajectories. However, the correlation between trajectories, which has not been given much attention to before, could also give rise to serious privacy leakage. Recent studies have proved that it is possible to identify social relationship, de-anonymize trajectories or even infer user’s locations by analyzing the correlation between users’ trajectories. We identify the serious privacy problem of social relationship leakage caused by what we call social relationship attack and aim to protect social relationship information, which cannot be protected by existing algorithms. We contribute to the design of a new privacy model and an effective system to deal with social relationship attack and re-identification attack simultaneously while maintaining high data utility. We propose aSlidingWindowalgorithm to merge trajectories according to theirsocial-aware distance, which concerns both the spatiotemporal distance and social proximity. Evaluations of two trajectory datasets under different scenarios demonstrate that our system provides more than 1.84 times privacy protection at the cost of only 2.5% data utility loss.

Social recommendation, which utilizes social relations to enhance recommender systems, has been gaining increasing attention recently with the rapid development of online social network. Existing social recommendation methods are based on the fact that users preference or decision is influenced by their social friends' behaviors. However, they assume that the influences of social relation are always the same, which violates the fact that users are likely to share preference on diverse products with different friends. In this paper, we present a novel CSR (short for C haracterized S ocial R egularization) model by designing a universal regularization term for modeling variable social influence. Our proposed model can be applied to both explicit and implicit iteration. Extensive experiments on a real-world dataset demonstrate that CSR significantly outperforms state-of-the-art social recommendation methods.

In this paper, we jointly consider partial offloading and resource allocation to minimize the sum latency with energy efficiency for multi-user mobile-edge computation offloading (MECO) system based on orthogonal frequency-division multiple access (OFDMA). We formulate mixed integer non- linear programming (MINLP) sum latency minimization problem considering the edge execution delay, desired energy consumption for local computation, OFDMA, QoS, transmission power in uplink and edge computation capacity constraints. We propose that a user can make use of multi-channel transmissions to reduce the transmission delay for task with large data size. We first derive an expression to determine optimal offloading fraction such that edge computing delay is less than the local execution delay and energy consumed for local execution does not exceed the desired limit. Then, we transform the original problem into communication and computation resource allocation problem and propose a suboptimal low complexity algorithm to find the resource allocation. The simulation results show that the proposed scheme achieves 17% and 25% better performance than random and complete offloading schemes, respectively.