In real-world time-series modelling, graph structures are widely adopted because they explicitly encode node topology and capture complex network dynamics. In practice, however, a complete graph is often partitioned across multiple parties; each party can access only its local sub-graph and, owing to privacy regulations, cannot share topology or data, creating pervasive data silos. Federated Graph Learning (FGL) offers a privacy-preserving collaborative-learning paradigm, yet current methods still face two key challenges: (1) the graph topology itself contains sensitive structural information, which can lead to privacy leakage if directly shared during FGL; (2) cross-party edges are crucial for accurate modeling, yet exploiting them without compromising privacy remains a significant challenge. To overcome these obstacles, we propose FedSkeleton, a privacy-preserving framework for time-series prediction that comprises a Skeleton Construction Module and a Dual-stream Forecasting Module, enabling global dependency capture without revealing the topology. Extensive experiments show that FedSkeleton consistently outperforms existing baselines and even surpasses models trained in a centralized setting with full-graph access in certain cases. In addition, we conduct comprehensive security analysis, communication-cost evaluation and scalability experiments, demonstrating that FedSkeleton effectively resists common attacks, keeps communication overhead manageable, and remains robust with respect to key hyper-parameters and the number of participating parties.

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.

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.

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.

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.

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.

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.

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.

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.

Modeling opinion dynamics in social networks has been the focus of multiple disciplines in recent decades. Previous studies have often modeled the opinion dynamics as a discrete and homogeneous process, neglecting its continuous and complex nature. To fill this gap, we propose a Bi-Dynamics Graph Ordinary Differential Equation (BDG-ODE) framework, which models complex opinion dynamics as the result of two dynamical processes: the evolution of positive and negative opinions. The proposed model incorporates a dual opinion encoder that processes positive and negative opinions independently. Furthermore, the temporal opinion evolution is modeled through bidirectional graph ordinary differential equations, which allows the model to capture the changes in opinion in continuous time. We introduce an opinion synthesis decoder that effectively maps the evolved representations from the latent space back to the opinion space. Extensive experiments conducted on six datasets with varying characteristics highlight the superiority of BDG-ODE in forecasting opinion evolution within social networks. It achieved an average accuracy improvement of 23.16%, an average enhancement of 29.46% in the F1 score, and an average mean square error of difference improvement of 90. 30%, and an average correlation coefficient improvement of 45.93%, significantly outperforming eight state-of-the-art models. The code for reproduction is available: https://github.com/tsinghua-fib-lab/Bi-Dynamic-Graph-ODE-for-Opinion-Evolution.

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.

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 ).

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.

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.

The energy consumption of 5G base stations (BSs) is significantly higher than that of 4G BSs, creating challenges for operators due to increased costs and carbon emissions. Existing solutions address this issue by switching off BSs during specific periods or forming cooperation coalitions where some BSs deactivate while others serve users. However, these approaches often rely on fixed geographic configurations, making them unsuitable for urban areas with numerous BSs and mobile users. To tackle these challenges, we propose a hierarchical reinforcement learning (RL) framework for energy conservation in large-scale 5G networks. In the upper-layer, we propose a deep Q-network integrated with a graph convolutional network that dynamically groups BSs into coalitions from a macro perspective. This layer focuses on high-level coalition formation to optimize system-wide energy efficiency by considering the global state of the network. In the lower-layer, we combine attention mechanism with multi-agent RL and graph convolutional networks to design a scalable algorithm that maximizes local energy efficiency through optimizing the cooperation within each coalition. These two layers align global coalition dynamics with local intra-coalition cooperation to achieve system-wide energy optimization. Moreover, we accurately model large-scale urban 5G scenarios leveraging a high-fidelity network simulator, which enables our RL framework to learn from real-world feedback. Extensive experiments conducted with the simulator demonstrate that our proposed framework achieves remarkable energy savings of up to 75.6%, significantly outperforming baseline approaches. These findings highlight the effectiveness and superiority of our hierarchical RL optimization framework in addressing the energy consumption challenges faced by large-scale 5G networks.

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.

The surge in core counts of modern processors has led to a notable reduction in available memory bandwidth per core. This paper introduces PSqueue, an enhanced memory scheduling queue architecture designed to optimize multithreaded streaming memory access on Loongson processors. The proposed architecture addresses two significant challenges identified in pre-silicon performance evaluations: the stalling of compression-based memory scheduling queue during rank-level refreshes and Network-on-Chip(NoC) congestion during highly intensive memory accesses. To mitigate these issues, PSqueue, the combination of a preprocessing queue and a selection-based memory scheduling queue, is introduced. The selection-based scheduling queue allows ready-to-issue requests to bypass blocked ones, enhancing out-of-order scheduling capabilities. The preprocessing queue alleviates congestion by providing an escape channel for memory requests, thereby increasing the overall throughput of the memory controller. Experimental results indicate that the PSqueue architecture achieves an average memory bandwidth gain of 4.04%, with peak gains of 6.48% in multi-threaded streaming memory access scenarios. These innovations are in preparation for the design of the next-generation Loongson processors.

The development of Internet of Things (IoT) systems has enabled disaster perception and prediction to be highly accurate. On this basis, high-quality post-disaster Point of Interest (POI) visit data can help city decision-makers develop more sophisticated recovery plans to minimize the cost of recovery. This work focuses on the problem of POI visits generation in post-disaster recovery scenarios, utilizing diffusion model to generate visit recovery curves base on the data from sensor networks. We take the disaster severity as condition and propose a disaster mapping method to map the sensor data to each POI.

Urban mobility undergoes a profound decline in the aftermath of a disaster, subsequently exhibiting a complex recovery trajectory. Effectively capturing and predicting this dynamic recovery process holds paramount importance for devising more efficient post-disaster recovery strategies, such as resource allocation to areas with protracted recovery periods. Existing models for post-disaster mobility recovery predominantly employ basic mathematical methods, which are strongly based on simplifying assumptions, and their limited parameters restrict their capacity to fully capture the mobility recovery patterns. In response to this gap, we introduce the Coupled Dynamic Graph ODE Network (CDGON) to model the intricate dynamics of post-disaster mobility recovery. Our model seamlessly integrates existing physical knowledge pertaining to post-disaster mobility recovery and incorporates the nuanced interactions between intra-regional and inter-regional population flows. Extensive experimental results demonstrate the efficiency of our model in capturing the dynamic recovery patterns of urban population mobility in post-disaster scenarios, surpassing the capabilities of current dynamic graph prediction models.

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.

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

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.

Daily activity data recording individuals’ various 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. However, existing solutions, including rule-based methods with simplified behavior assumptions and data-driven methods directly fitting real-world data, both cannot fully qualify for matching reality. In this article, 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. Our core idea is to model the evolution of human needs as the underlying mechanism that drives activity generation in the simulation model. Specifically, a hierarchical model structure that disentangles different need levels and the use of neural stochastic differential equations successfully capture the piecewise-continuous characteristics of need dynamics. Extensive experiments demonstrate that our framework outperforms the state-of-the-art baselines regarding data fidelity and utility. We also present the insightful interpretability of the need modeling. Moreover, privacy preservation evaluations validate that the generated data does not leak individual privacy. The code is available at https://github.com/tsinghua-fib-lab/Activity-Simulation-SAND .

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.

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

Synthesized human trajectories are instrumental for a large number of applications. However, existing trajectory synthesizing models are limited in either modeling variable-length trajectories with continuous temporal distribution or incorporating multi-dimensional context information. In this paper, we propose a novel probabilistic model based on the variational temporal point process to synthesize human trajectories. This model combines the classical temporal point process with the novel neural variational inference framework, leading to its strong ability to model human trajectories with continuous temporal distribution, variable length, and multi-dimensional context information. Extensive experimental results on two real-world trajectory datasets show that our proposed model can synthesize trajectories most similar to real-world human trajectories compared with four representative baseline algorithms in terms of a number of usability metrics, demonstrating its effectiveness.

Recently, artificial intelligence paves the way for the development of smart services for people anytime and anywhere, which poses great challenges on accessing computing resources. Multi-access edge computing complements existing cloud computing infrastructure at the edge of the network, where mobile users can offload computationally intensive tasks of smart applications to edge servers that are in proximity to the users themselves. Existing offloading schemes mainly focus on selecting edge servers for each offloading task with the goal of optimizing the overall average latency. However, the solutions with the optimal overall average latency may be not the most suitable for all offloading tasks. There is still a possibility that offloading leads to an extreme case of ultra-high latency, which is not acceptable for latency-sensitive applications. To address this problem, we therefore introduce modern portfolio theory (MPT) to jointly consider the overall average latency and potential risks in optimal edge server selection. The task offloading problem is regarded as an investment portfolio with the objective of maximizing the ‘return’ while minimizing the risk. Combining MPT with deep reinforcement learning (DRL), we design two proximal policy optimization (PPO)-based task offloading algorithms to jointly optimize these two objectives. The algorithm computes a portfolio for each mobile user that enables the diversification of edge server selection, thereby minimizing the risk and the average latency. Extensive simulation results based on three real-world trace datasets show that our algorithms significantly outperform the state-of-the-art solutions and can reduce the overall average latency and the risk by 59% and 85% at most, respectively.

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 .

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.

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.

The sign-sign least-mean-squares (SSLMS) algorithm has been widely used in decision feedback equalizer (DFE) adaptation. However, the convergence direction of DFE tap coefficients in the training process is closely related to the data flow. In the case of extreme data flow, the coefficients may converge to inaccurate values, resulting in DFE sampling errors. This article proposes a novel light-pattern-protection (LPP) algorithm to achieve robustness. The LPP guarantees the convergence direction in extreme data flow and brings no loss of convergence rate in a balanced situation. Another advantage of LPP is good scalability, which can be demonstrated in two points. One point is that the convergence time does not increase as the number of DFE taps. The other is that extending the algorithm to the traditional SSLMS scheme requires insignificant hardware and power consumption.

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.

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.

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.

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.

The emerging network-softwarization technologies, such as software-defined networking and network function virtualization play important roles in 5G communication and future networks. One of the critical challenges of the practical application of the softwarized networks is to appropriately place virtual network functions (VNFs). The underlying resources and traffic requirements are often factored in the previous works of VNF placement. However, VNFs’ dynamic abilities of changing traffic are usually ignored. Resources allocated to VNFs can vary their traffic-change ratios, and the adjustment of resource volumes should be provisioned to support traffic changes. In this work, we pay attention to the joint optimization problem of VNF Placement, CPU Allocation, and flow Routing (VNFPAR) in the scenarios consisting of VNFs that can dynamically change traffic. We employ the logarithmic functions to approximate VNFs’ traffic change relations and formulate VNFPAR as a mixed-integer nonlinear programming (MINLP) problem. We demonstrate that this problem is highly nonconvex and involves highly coupled variables. For small-scale VNFPAR problems, we propose an optimal algorithm based on relaxation and programming to consume the minimum bandwidth resources. Because VNFPAR is NP-hard, to quickly find near-optimal solutions for large-scale VNFPAR problems, we present heuristic algorithms based on multistage greedy and simulated annealing, respectively. Besides, to achieve a tradeoff between solution quality and execution time, we decompose VNFPAR into subproblems and design an alternating optimization-based method. We evaluate our algorithms on real-work topologies and traffic patterns. Extensive simulations show that our proposed heuristic algorithms are convergent, stable, and effective in terms of solving VNFPARs. The proposed algorithms have small optimality gaps within 7.4%–26.3%. Meanwhile, they save 39.3%–48.4% bandwidth resources compared with relevant baseline technologies.

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.

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.

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 widespread use of mobile devices in recent years, accurate prediction of base station traffic is vital for maintaining a good quality of mobile network services. In this paper, we propose an ensemble learning framework to predict the cellular traffic of base stations. Specifically, we introduce the Granger causality test to find the causal relationship in the base stations and model the spatial relationship between them simultaneously. We also employ a temporal convolutional network (TCN) to extract the sequential temporal features of base station traffic. Aiming at modelling the long-tail characteristics of the traffic distribution of base stations, we use the technique of redundant encoding to refine the prediction task to learn the base station traffic of different scales combined with ensemble learning. Extensive experimental results demonstrate that our method can predict base station traffic precisely and outperforms the best baseline by nearly 13% on average in terms of NMSE and NRMSE.

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.

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.

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.

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.

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%.

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.

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.

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.

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.

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.

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.

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%.

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.

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.

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.

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.

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.

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.

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 paper, we propose a novel system to link IDs across multiple services by exploring the spatial-temporal locality of user activities. 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 ISP (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 matching order and number of services.

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.

In the modern information society, accurate prediction 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. In this paper, based on a dataset of 100,000 individuals' actively uploaded location information collected by apps, we discover the average theoretical limits of the predictability to be as high as 93%. Since the app-collected data contains the physical context of the location, we implement a clustering method based on the contextual information that cluster the locations into three divisions, street, district and region. In order to solve the unevenly distribution and the high missing rate of the application collected location data, we firstly use the Gibbs sampling algorithm to complete the missing data of the trajectory and then employ a high-order Markov chain model to predict the most likely locations visited by each user. Result shows that our prediction algorithm can achieve accuracy as high as 67%, 78%, 87% for the three context-based divisions respectively, which are 10% higher on average than the divisions without context. In addition, the correlation coefficient between prediction accuracy and predictability reaches as high as 0.86. Finally, we investigate various factors including spatial and temporal resolution, orders of Markov models, radius of gyration, in order to explore the predictability under different circumstances.

Understanding mobile traffic patterns of large scale cellular towers in urban environment is extremely valuable for Internet service providers, mobile users, and government managers of modern metropolis. This paper aims at extracting and modeling the traffic patterns of large scale towers deployed in a metropolitan city. To achieve this goal, we need to address several challenges, including lack of appropriate tools for processing large scale traffic measurement data, unknown traffic patterns, as well as handling complicated factors of urban ecology and human behaviors that affect traffic patterns. Our core contribution is a powerful model which combines three dimensional information (time, locations of towers, and traffic frequency spectrum) to extract and model the traffic patterns of thousands of cellular towers. Our empirical analysis reveals the following important observations. First, only five basic time-domain traffic patterns exist among the 9600 cellular towers. Second, each of the extracted traffic pattern maps to one type of geographical locations related to urban ecology, including residential area, business district, transport, entertainment, and comprehensive area. Third, our frequency-domain traffic spectrum analysis suggests that the traffic of any tower among 9600 can be constructed using a linear combination of four primary components corresponding to human activity behaviors. We believe that the proposed traffic patterns extraction and modeling methodology, combined with the empirical analysis on the mobile traffic, pave the way toward a deep understanding of the traffic patterns of large scale cellular towers in modern metropolis.

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 them through multiple online identifiers (IDs), and interact with each other in both the cyberspace and the physical world. These two kinds of interactions are highly relevant to 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 interactions when people come across each other. By analyzing real data collected from a mainstream ISP in China, which contains 32.7 million IDs across most popular web services, we build a large-scale CLSN, and evaluate its unique properties. The results verify that the CLSN is quite different from existing online and offline social networks in terms of different classic graph metrics. This paper is the first research to study CLSN at scale and paves the way for future studies of this new type of social network.

As power consumption of the Internet has been growing quickly in recent years, saving energy has become an important problem of networking research, for which the most promising solution is to find the minimum-power network subsets and shut down other unnecessary network devices and links to satisfy changing traffic loads. However, in traditional networks, it is difficult to implement a coordinated strategy among the network devices due to their distributed network control. On the other hand, the new networking paradigm-software defined network (SDN) provides us an efficient way of having a centralized controller with a global network view to control the power states. As an emerging technology, SDNs usually coexist with traditional networks at present. Therefore, we need to investigate how to save energy in partially deployed SDNs. In this paper, we formulate the optimization problem of finding minimum-power network subsets in partially deployed SDNs. After proving the problem is NP-hard, we propose a heuristic solution to approach its exact solution. Through extensive simulations, we demonstrate that our heuristic algorithm has a good performance; that is, on average we can save about 50 percent of total power consumption in the full SDN, having a distance less than 5 percent of the exact solution's power consumption. Moreover, it also achieves good performance in the partially deployed SDN, on average saving about 40 percent of the total power consumption when there are about 60 percent SDN nodes in the network. Meanwhile, it runs significantly faster than a general linear solver of this problem, by reducing the computation time of the network containing hundreds of nodes by 100× at least.

Understanding mobile traffic patterns of large scale cellular towers in urban environment is extremely valuable for Internet service providers, mobile users, and government managers of modern metropolis. This paper aims at extracting and modeling the traffic patterns of large scale towers deployed in a metropolitan city. To achieve this goal, we need to address several challenges, including lack of appropriate tools for processing large scale traffic measurement data, unknown traffic patterns, as well as handling complicated factors of urban ecology and human behaviors that affect traffic patterns. Our core contribution is a powerful model which combines three dimensional information (time, locations of towers, and traffic frequency spectrum) to extract and model the traffic patterns of thousands of cellular towers. Our empirical analysis reveals the following important observations. First, only five basic time-domain traffic patterns exist among the 9,600 cellular towers. Second, each of the extracted traffic pattern maps to one type of geographical locations related to urban ecology, including residential area, business district, transport, entertainment, and comprehensive area. Third, our frequency domain traffic spectrum analysis suggests that the traffic of any tower among the 9,600 can be constructed using a linear combination of four primary components corresponding to human activity behaviors. We believe that the proposed traffic patterns extraction and modeling methodology, combined with the empirical analysis on the mobile traffic, pave the way toward a deep understanding of the traffic patterns of large scale cellular towers in modern metropolis.

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. Through extensive simulations, we demonstrate that our fully polynomial time approximation (FPTA) algorithm has a good performance compared with the optimal solution and two state-of-the-art algorithms. That is, our proposed FPTA algorithm approaches to the optimal solution with less than 10% variation and much less computation time. Meanwhile, it reduces the total migration time and the service downtime by up to 40% and 20% compared with the state-of-the-art algorithms, respectively.

Since multi-core processor and System-On-Chip (SOC) have developed fast in recent years, the interconnection bus becomes a key factor to system performance. Recently, it is reported that for most desktop and embedded systems, bus bandwidth has not been fully exploited, and the data transfer efficiency is low. In this paper, we show that the frequent cross-domain bus transaction is the main bottleneck of I/O performance promotion. Then based on a Hyper Transport (HT) 3.0 bus controller design, we propose an optimization scheme which includes a pipelined design methodology for cross-domain bus transaction and asynchronous FIFO designs using Globally Ratiochronous Locally Synchronous (GRLS) technology. The experiment shows that our solution increases the HT bus read and write bandwidths about 34.8% and 13.5% respectively, and it reduces the latency about 40%. Although our solution is based on well known system buses technologies - AMBA AXI and HT bus technologies, it can be easily implemented in systems with other bus technologies.

We propose a novel architecture of memory controller, called HMC (Heterogeneous Multi-Channel), as an improvement to the previous homogeneous multi-channel memory controller. HMC groups physical DRAM devices into logical sub-ranks with different data bus width, and controls them simultaneously. Employing new proposed memory access algorithm, HMC manages the number of devices involved in a single memory access flexibly, and achieves the best performance/power efficiency. Using four-core multiprogramming workloads, our experimental results show that HMC improves system performance by 27.6% with 24.2% reduction in DRAM power consumption on average.

This paper presents a new memory access scheduler, called FSCM (Fair Service Curve Memory access scheduler), which targets for the objective that provides the highest system throughput. The main idea of reordering memory access requests based on the service curve is borrowed from the literature of packet-switched networks. Different threads have different QoS (Quality-of-Service) requirements, and FSCM assigns each thread a service curve. The service curve gives great adaptability to FSCM in allocating its bandwidth. We evaluate FSCM using multi-threaded applications, and compare it to three previously proposed memory access schedulers. On a four-core CMP running combinations of workloads with a wide range of memory bandwidth and latency requirements, FSCM improves system performance by 16.7% on average, and provides the best fairness to all of the threads.

GALS combined with Frequency Scaling has become a popular and effective technique in chip power reduction. However, frequency switching penalty and crossing-domain communication may be harmful to the performance of design. This paper proposes a Counter Based Variable Frequency Scaling (CB-VFS) scheme with zero latency for frequency switching. Based on CB-VFS, a Robust Instant-responding Ratiochronous Interface (RIRI) scheme is presented. Synchronous mechanisms are employed to simplify and justify the timing analysis. In particular, it has zero-latency crossing domain penalty. Simulation results of a synthesizable RIRI scheme based memory system demonstrate its efficiency.

This paper describes a multi-FPGA based platform for emulating the Loongson-2G micro-processor on different mother boards. This platform is developed targeting at verification and evaluation of the Loongson-2G micro-processor, which is the next generation of Loongson-2 family, composed by one four-issue, out-of-order execution way 64-bit MIPS-compatible processor core named GS464, one 1M byte secondary Cache, one HyperTransport IO interface, one DDR2/3 memory interface and some other low speed IO interfaces. Most parts of this micro-process are mapped into the multi-FPGA based platform which consists two Vertex-5 330 FPGA chips. Semi-custom partitioning tactics within the entire design flow are developed to synthesize the whole designed into the multi-FPGA based platform. Modifications in architectural level are applied to the original architecture of the chip, in order to make it easy to be partitioned into two parts. High speed SEDES of HyperTransport IO link and DDR2/3 memory interface are emulated by using several clocks with different clock phases. To resolve the problem that hard to debug in FPGA system, a method by software probe with help of injected hardware modules in FPGA is developed and used to debug the problem causing by behavior mismatching between the ASIC ram block and the FPGA ram block. Some evaluation work on performance of Loongson-2G is done on this multi-FPGA based platform as pre-silicon test. To the authors' knowledge, there has been no previous work on such a big design used for verification and evaluation.

HyperTransport link is a high performance IO interface for system connection. In this paper, the architecture of a HyperTransport interface is introduced. This HyperTransport interface realizes efficient HT-AXI bidirectional transformation, where AXI is a popular bus protocol in SOC architectures. Furthermore, this HyperTransport interface provides dedicated hardware support for cache coherence protocol. Through this HyperTransport interface, Godson-3A multi-core processor chips can be interconnected together to form a 4-16 core CC-NUMA system or a large-scale NCCNUMA system. The verification of the HyperTransport interface is also presented.