With the wide adoption of online education platforms, adaptive learning systems have become increasingly important. Learning Path Recommendation (LPR) aims to dynamically adjust learning content to optimize learning efficiency based on individual student needs. However, current LPR methods suffer from sparse reward for precise assessment and only focus on anonymous sessions that overlook more personalized and effective paths. To address these challenges, we propose UNO, UNified Offline Training Paradigm for Learning Path Recommendation. This approach introduces an offline training paradigm in RL-based LPR to provide dense process rewards by a personalized advantage based on a reward model, which can estimate the students' internal knowledge levels on the learning targets. Additionally, we propose UniLPR model, a personalized recommendation system that unifies modeling the implicit relationships between students' long-term accumulation and evolving requirements for questions, and refines through Group Relative Policy Optimization(GRPO). Finally, we design learning tasks that encompass historical reviewing, recent learning, and long-term exploratory learning to simulate the comprehensive and diverse learning needs of students. Our UNO achieves state-of-the-art performance across all tasks, demonstrating its effectiveness.

As reliable distributed systems, Blockchains have been widely applied in diverse domains, such as the Internet of Things (IoT). Recent studies have explored Deep Reinforcement Learning (DRL) to enhance blockchain performance. However, existing DRL-based blockchain performance optimization methods rely on implicit and idealized assumptions about node behaviors and transactional workloads, limiting their effectiveness and efficiency on the blockchain with dynamic work-loads and heterogeneous nodes. To alleviate this, we propose CHAINOPT, a novel blockchain performance optimization framework devised for optimal parameter configuration to handle dynamic workloads and heterogeneous nodes. Specifically, we first propose an interaction-aware state representation learning module to model both global system-level and local heterogeneous node feature interactions to generate better state representations. Then, a contrastive learning-enhanced workload identification module is designed to extract discriminative workload-specific state representations to improve workload identification accuracy. Finally, we design a workload-similarity guided policy reuse module to produce effective reuse weights to transfer knowledge from history policies based on workload relevance, thereby improving optimization speed and stability. Extensive experiments show the effectiveness of CHAINOPT in improving blockchain performance, achieving 185.87% higher scalability and 1492.16% stronger security with only a marginal 6.26% latency increase. Moreover, it outperforms baselines in static scenarios while maintaining considerable superiority under varying workloads.

Path representations are widely applied in smart-city tasks, such as travel time estimation, road classification, and trajectory search. Existing approaches effectively learn these representations by jointly utilizing multi-mode data, including GPS trajectories, road paths, and road networks. Although these methods achieve state-of-the-art performance, the theoretical understanding of the importance and effectiveness of key designs in path representation pre-training remains unclear. Moreover, these methods often rely on hard-constrained labeled data and manual design, resulting in limited performance gains and high annotation costs. In this paper, we proposeSimPRL, a simple yet powerful contrastive learning framework that capitalizes on unannotated data. Building on the exploration of key factors contributing to successful path representation learning, SimPRL integrates unannotated GPS trajectories and road paths directly through contrastive self-supervised learning. Specifically, we introduce a pre-training task that predicts correspondences between trajectories from different modes using a shared encoder, without requiring labeled data. We also design an auxiliary segment imputation task and a minimal trajectory sampling technique with random offsets for data augmentation. Additionally, we employ any trajectory within the mini-batch, except for the anchor itself, as the negative sample. Extensive experiments on two large-scale, real-world datasets from Chengdu and Porto demonstrate the effectiveness of SimPRL in two downstream tasks: travel time estimation and road classification. The results show that SimPRL not only surpasses state-of-the-art methods but also achieves more stable generalization and greater efficiency in terms of runtime and memory usage. Our source code is available athttps://github.com/TXLiao/SimPRL

Large-scale human mobility data contains rich spatial and temporal information for urban sensing, crowd flow modeling, and urban planning. However, it is usually difficult to access wide-coverage, long-term, and consistent-time human mobility data. Most of the publicly available datasets are actually only records of discontinuous trajectories of a very small portion of urban citizens in asynchronous time due to the limited usage of apps for location data collection or the limited number of volunteers. To address this problem and empower open urban research, this paper constructs a high-quality human mobility dataset by generating large-scale citizen trajectories based on massive cellular signaling data. Particularly, we first propose a heatmap diffusion module to generate a probability heatmap that produces plausible trajectories at both the individual and city scales. Then, we propose a masked trajectory AutoEncoder, which can generate individual trajectory embeddings from partially given or empty trajectories. Third, a flexible framework is provided to incorporate the heatmap diffusion module with the masked trajectory embeddings, demonstrating significant flexibility in handling both fully masked trajectories for city-wide analysis and partially masked trajectories for specific locations. We have conducted extensive experiments to validate the utility of the regenerated trajectories at both individual and region levels for various applications. Numerous case studies further illustrate that our model learns not only the distribution of the trajectories but also the semantics of different urban areas.

In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. However, policies tuned for cooperation often fail to maintain robustness and resilience under real-world uncertainties. Building trustworthy MARL systems requires a deep understanding of \emph{robustness}, which ensures stability under uncertainties, and \emph{resilience}, the ability to recover from disruptions—a concept extensively studied in control systems but largely overlooked in MARL. In this paper, we present a large-scale empirical study comprising over 82,620 experiments to evaluate cooperation, robustness, and resilience in MARL across 4 real-world environments, 13 uncertainty types, and 15 hyperparameters. Our key findings are: (1) Under mild uncertainty, optimizing cooperation improves robustness and resilience, but this link weakens as perturbations intensify. Robustness and resilience also varies by algorithm and uncertainty type. (2) Robustness and resilience do not generalize across uncertainty modalities or agent scopes: policies robust to action noise for all agents may fail under observation noise on a single agent. (3) Hyperparameter tuning is critical for trustworthy MARL: surprisingly, standard practices like parameter sharing, GAE, and PopArt can hurt robustness, while early stopping, high critic learning rates, and Leaky ReLU consistently help. By optimizing hyperparameters only, we observe substantial improvement in cooperation, robustness and resilience across all MARL backbones, with the phenomenon also generalizing to robust MARL methods across these backbones.

Abstract Reasoning has long been regarded as a distinctive hallmark of human cognition, and recent advances in the artificial intelligence community have increasingly focused on the reasoning large language models (rLLMs). However, due to strict privacy regulations, the domain-specific reasoning knowledge is often distributed across multiple data owners, limiting the rLLM’s ability to fully leverage such valuable resources. In this context, federated learning (FL) has gained increasing attention in both the academia and industry as a promising privacy-preserving paradigm for addressing the challenges in the data-efficient training of rLLMs. In this paper, we conduct a comprehensive survey on federated rLLMs and propose a novel taxonomy based on training signals, including training signals derived from raw data, learned representations, and preference feedback. For each category, we emphasize the emerging trends according to how to use FL to enhance reasoning capabilities of rLLMs considering the model effectiveness, communication cost and privacy preservation. Finally, we envision future research directions and challenges based on insights from existing studies.

Information diffusion prediction, aimed at estimating future interacting users for a given content, is crucial for various applications on online social platforms. Recently, methods based on dynamic graph learning have achieved superior performance. However, these methods often face scalability issues due to their full-neighbor aggregation, which requires loading the whole diffusion graph, making them impractical for large graphs. While improving model scalability through sampling is an immediate approach, it is challenging on the diffusion graph due to various user dependencies (i.e., the temporal and structural correlations of user–item interactions). To address this problem, we propose a new model named ASDIP, which performs adaptive sampling on the diffusion graph. Specifically, ASDIP employs multiple sampling strategies to extract walks from the diffusion graph, each identifying a representative user dependency by sampling walks that satisfy a specific temporal constraint. Next, the walks sampled by different strategies are first mapped into distinct strategy-specific user representations and then merged into a unified user representation, adaptively fusing the information obtained from different strategies. Finally, a cascade representation learning module is proposed to generate cascade representations based on user representations and interaction timestamps. Experimental results validate the effectiveness and scalability of ASDIP.

Temporal link prediction, aiming at predicting future interactions among entities based on historical interactions, is crucial for a series of real-world applications. Although previous methods have demonstrated the importance of relative encodings for effective temporal link prediction, computational efficiency remains a major concern in constructing these encodings. Moreover, existing relative encodings are usually constructed based on structural connectivity, where temporal information is seldom considered. To address the aforementioned issues, we first analyze existing relative encodings and unify them as a function of temporal walk matrices. This unification establishes a connection between relative encodings and temporal walk matrices, providing a more principled way for analyzing and designing relative encodings. Based on this analysis, we propose a new temporal graph neural network called TPNet, which introduces a temporal walk matrix that incorporates the time decay effect to simultaneously consider both temporal and structural information. Moreover, TPNet designs a random feature propagation mechanism with theoretical guarantees to implicitly maintain the temporal walk matrices, which improves the computation and storage efficiency. Experimental results on 13 benchmark datasets verify the effectiveness and efficiency of TPNet, where TPNet outperforms other baselines on most datasets and achieves a maximum speedup of $33.3 \times$ compared to the SOTA baseline.

In the realm of video analytics, the significance of video anomaly detection cannot be ignored. Many video anomaly detection methods have been introduced in traffic scenarios, and they have achieved some promising results. However, there still exists a large room for improving the traffic anomaly detection performance. In this paper, we present an end-to-end approach, the Dual-Stream Anomaly Detection Network (DS-ADN), specialized for traffic anomaly detection. DS-ADN introduces optical flow data and utilizes inter-flow information interaction coupled with the Multi-Scale Attention Fusion Module (MSA-FM) to comprehensively merge RGB and optical flow data. It features an innovative depth-based prediction loss function that adapts to the vehicle’s regular shape and events at different distances under the surveillance camera. This adaptation occurs through block-wise average pooling and weighted allocation across varying depths. Considering the prevalent issues of datasets dedicated to traffic anomaly detection generally containing a single type of anomaly, this paper introduces the Traffic Surveillance Dataset (TSD) containing multiple anomalies for model validation. Extensive experiments on the TSD dataset highlight the better performance of our DS-ADN, manifesting an AUC gain of over 8.8% compared to other state-of-the-art models. Moreover, DS-ADN achieves competitive performance across three widely-used anomaly detection datasets that contain multiple anomalies, including UCSD Ped2, Avenue, and ShanghaiTech, demonstrating its generalization ability.

Origin-Destination demand prediction is a fundamental and important task in the urban transportation system. It is more challenging and complex than region demand prediction since it needs to predict traffic demand for each pair of regions rather than a single region, which means$N^{2}$time series need to be predicted given$N$stations. Most existing works are mainly proposed for the region (or station) demand prediction. On the other hand, previous Origin-Destination demand prediction methods only follow a single discrete-time setting while the input data are continuous-time OD orders, which means these methods have not sufficiently leveraged the rich information for demand prediction. To solve these challenges, we propose a novel framework consisting of both continuous-time and discrete-time representation learning modules for Origin-Destination demand prediction. Firstly, we construct memorable representations of all nodes and design a continuous-time learning module to update the nodes’ representations once a time-stamped OD transaction is observed. Then, a discrete-time representation learning module is proposed to generate discrete-time messages containing information across a fixed time interval from a macro perspective. Next, a co-updater module is designed to fuse messages from both continuous-time and discrete-time channels into node memory. Last, a graph attention module is developed, which generates final node embeddings using updated node memory and predicts the forthcoming OD demand matrix based on them. The experimental results on real-world datasets show that our method leads to significant and consistent improvements compared to other methods.

Given a sequence of sets, where each set has a timestamp and contains an arbitrary number of elements, temporal sets prediction aims to predict the elements in the subsequent set. Previous studies for temporal sets prediction mainly focus on the modelling of elements and implicitly represent each user's preference based on his/her interacted elements. However, user preferences are often continuously evolving and the evolutionary trend cannot be fully captured with the indirect learning paradigm of user preferences. To this end, we propose a continuous-time user preference modelling framework for temporal sets prediction, which explicitly models the evolving preference of each user by maintaining a memory bank to store the states of all the users and elements. Specifically, we first construct a universal sequence by arranging all the user-set interactions in a non-descending temporal order, and then chronologically learn from each user-set interaction. For each interaction, we continuously update the memories of the related user and elements based on their currently encoded messages and past memories. Moreover, we present a personalized user behavior learning module to discover user-specific characteristics based on each user's historical sequence, which aggregates the previously interacted elements from dual perspectives according to the user and elements. Finally, we develop a set-batch algorithm to improve the model efficiency, which can create time-consistent batches in advance and achieve 3.5× and 3.0× speedups in the training and evaluation process on average. Experiments on four real-world datasets demonstrate the superiority of our approach over state-of-the-arts under both transductive and inductive settings. The good interpretability of our method is also shown.

Designing new molecules is essential for drug discovery and material science. Recently, deep generative models that aim to model molecule distribution have made promising progress in narrowing down the chemical research space and generating high-fidelity molecules. However, current generative models only focus on modeling 2-D bonding graphs or 3-D geometries, which are two complementary descriptors for molecules. The lack of ability to jointly model them limits the improvement of generation quality and further downstream applications. In this article, we propose a joint 2-D and 3-D graph diffusion model (JODO) that generates geometric graphs representing complete molecules with atom types, formal charges, bond information, and 3-D coordinates. To capture the correlation between 2-D molecular graphs and 3-D geometries in the diffusion process, we develop a diffusion graph transformer (DGT) to parameterize the data prediction model that recovers the original data from noisy data. The DGT uses a relational attention mechanism that enhances the interaction between node and edge representations. This mechanism operates concurrently with the propagation and update of scalar attributes and geometric vectors. Our model can also be extended for inverse molecular design targeting single or multiple quantum properties. In our comprehensive evaluation pipeline for unconditional joint generation, the experimental results show that JODO remarkably outperforms the baselines on the QM9 and GEOM-Drugs datasets. Furthermore, our model excels in few-step fast sampling, as well as in inverse molecule design and molecular graph generation. Our code is provided in https://github.com/GRAPH-0/JODO.

Given a sequence of sets, where each set contains an arbitrary number of elements, temporal sets prediction aims to predict which elements will appear in the subsequent set. Existing methods for temporal sets prediction are developed on sophisticated components (e.g., recurrent neural networks, attention or gating mechanisms, and graph neural networks), which inevitably increase the model complexity due to more trainable parameters and higher computational costs. Moreover, the involved nonlinear activation may contribute little or even degrade the performance. In this paper, we present a succinct architecture that is solely built on the Simplified Fully Connected Networks (SFCNs) for temporal sets prediction to bring both effectiveness and efficiency together. In particular, given a user's sequence of sets, we employ SFCNs to derive representations of the user by learning inter-set temporal dependencies, intra-set element relationships, and intra-embedding channel correlations. Two families of general functions are introduced to preserve the permutation-invariant property of each set and the permutation-equivariant property of elements in each set. Moreover, we design a user representations adaptive fusing module to aggregate user representations according to each element for improving the prediction performance. Experiments on four benchmarks show the superiority of our approach over the state-of-the-art under both transductive and inductive settings. We also theoretically and empirically demonstrate that our model has lower space and time complexity than baselines. Codes and datasets are available at https://github.com/yule-BUAA/SFCNTSP.

Learning the underlying distribution of molecular graphs and generating high-fidelity samples is a fundamental research problem in drug discovery and material science. However, accurately modeling distribution and rapidly generating novel molecular graphs remain crucial and challenging goals. To accomplish these goals, we propose a novel Conditional Diffusion model based on discrete Graph Structures (CDGS) for molecular graph generation. Specifically, we construct a forward graph diffusion process on both graph structures and inherent features through stochastic differential equations (SDE) and derive discrete graph structures as the condition for reverse generative processes. We present a specialized hybrid graph noise prediction model that extracts the global context and the local node-edge dependency from intermediate graph states. We further utilize ordinary differential equation (ODE) solvers for efficient graph sampling, based on the semi-linear structure of the probability flow ODE. We also combine the solvers with gradient guidance from the molecule property predictor for similarity-constrained molecule optimization. Experiments on diverse datasets validate the effectiveness of our framework. Particularly, the proposed method still generates high-quality molecular graphs in a limited number of steps.

We propose DyGFormer, a new Transformer-based architecture for dynamic graph learning. DyGFormer is conceptually simple and only needs to learn from nodes' historical first-hop interactions by: (1) a neighbor co-occurrence encoding scheme that explores the correlations of the source node and destination node based on their historical sequences; (2) a patching technique that divides each sequence into multiple patches and feeds them to Transformer, allowing the model to effectively and efficiently benefit from longer histories. We also introduce DyGLib, a unified library with standard training pipelines, extensible coding interfaces, and comprehensive evaluating protocols to promote reproducible, scalable, and credible dynamic graph learning research. By performing exhaustive experiments on thirteen datasets for dynamic link prediction and dynamic node classification tasks, we find that DyGFormer achieves state-of-the-art performance on most of the datasets, demonstrating its effectiveness in capturing nodes' correlations and long-term temporal dependencies. Moreover, some results of baselines are inconsistent with previous reports, which may be caused by their diverse but less rigorous implementations, showing the importance of DyGLib. All the used resources are publicly available at https://github.com/yule-BUAA/DyGLib.

Ride hailing has become prevailing. Central in ride hailing platforms is taxi order dispatching which involves recommending a suitable driver for each order. Previous works use pure combinatorial optimization solutions for taxi dispatching, which suffer in practice due to complex dynamics of demand and supply and temporal dependency among dispatching decisions. Recent studies try to adopt data-driven method into combinatorial optimization hoping knowledge from history data would help overcome these challenges. Among these attempts, adoption of reinforcement learning shows great promise but current adoptions are a unidirectional integration which restricts the potential performance gains. In this work, we proposeLearningToDispatch(LTD), a systematic solution that allows synergic integration of reinforcement learning and combinatorial optimization for large-scale taxi order dispatching. We demonstrate the necessity of online learning and taxi scheduling for reinforcement learning to work in synergy with combinatorial optimization, and devise corresponding algorithms. We also devise many tricks for more efficient calculation of the bipartite matching. Experiments show our methods can improve$36.4\%$and$42.0\%$on utility and efficiency at most, respectively. Especially, it achieves state-of-the-art performance in terms of utility.

Representation learning on heterogeneous graphs aims to obtain meaningful node representations to facilitate various downstream tasks. Existing heterogeneous graph learning methods are primarily developed by following the propagation mechanism of node representations. There are few efforts on studying the role of relations for improving the learning of more fine-grained node representations. Indeed, it is important to collaboratively learn the semantic representations of relations and discern node representations with respect to different relation types. In this paper, we propose a novel Relation-aware Heterogeneous Graph Neural Network (R-HGNN), to learn node representations on heterogeneous graphs at a fine-grained level by considering relation-aware characteristics. Specifically, a dedicated graph convolution component is first designed to learn unique node representations from each relation-specific graph separately. Then, a cross-relation message passing module is developed to improve the interactions of node representations across different relations. Also, the relation representations are learned in a layer-wise manner to capture relation semantics, which are used to guide the node representation learning process. Moreover, a semantic fusing module is presented to aggregate relation-aware node representations into a compact representation with the learned relation representations. Experimental results on extensive graph learning tasks demonstrate that our approach could consistently outperform existing methods.

Graph Neural Networks (GNNs) have been widely applied in the semi-supervised node classification task, where a key point lies in how to sufficiently leverage the limited but valuable label information. Most of the classical GNNs solely use the known labels for computing the classification loss at the output. In recent years, several methods have been designed to additionally utilize the labels at the input. One part of the methods augment the node features via concatenating or adding them with the one-hot encodings of labels, while other methods optimize the graph structure by assuming neighboring nodes tend to have the same label. To bring into full play the rich information of labels, in this article we present a label-enhanced learning framework for GNNs, which first models each label as a virtual center for intra-class nodes and then jointly learns the representations of both nodes and labels. Our approach could not only smooth the representations of nodes belonging to the same class, but also explicitly encode the label semantics into the learning process of GNNs. Moreover, a training node selection technique is provided to eliminate the potential label leakage issue and guarantee the model generalization ability. Finally, an adaptive self-training strategy is proposed to iteratively enlarge the training set with more reliable pseudo labels and distinguish the importance of each pseudo-labeled node during the model training process. Experimental results on both real-world and synthetic datasets demonstrate our approach can not only consistently outperform the state-of-the-arts, but also effectively smooth the representations of intra-class nodes.

Graph generative models have broad applications in biology, chemistry and social science. However, modelling and understanding the generative process of graphs is challenging due to the discrete and high-dimensional nature of graphs, as well as permutation invariance to node orderings in underlying graph distributions. Current leading autoregressive models fail to capture the permutation invariance nature of graphs for the reliance on generation ordering and have high time complexity. Here, we propose a continuous-time generative diffusion process for permutation invariant graph generation to mitigate these issues. Specifically, we first construct a forward diffusion process defined by a stochastic differential equation (SDE), which smoothly converts graphs within the complex distribution to random graphs that follow a known edge probability. Solving the corresponding reverse-time SDE, graphs can be generated from newly sampled random graphs. To facilitate the reverse-time SDE, we newly design a position-enhanced graph score network, capturing the evolving structure and position information from perturbed graphs for permutation equivariant score estimation. Under the evaluation of comprehensive metrics, our proposed generative diffusion process achieves competitive performance in graph distribution learning. Experimental results also show that GraphGDP can generate high-quality graphs in only 24 function evaluations, much faster than previous autoregressive models.

Traffic demand forecasting by deep neural networks has attracted widespread interest in both academia and industry society. Among them, the pairwise Origin-Destination (OD) demand prediction is a valuable but challenging problem due to several factors: (i) the large number of possible OD pairs, (ii) implicitness of spatial dependence, and (iii) complexity of traffic states. To address the above issues, this paper proposes a Continuous-time and Multi-level dynamic graph representation learning method for Origin-Destination demand prediction (CMOD). Firstly, a continuous-time dynamic graph representation learning framework is constructed, which maintains a dynamic state vector for each traffic node (metro stations or taxi zones). The state vectors keep historical transaction information and are continuously updated according to the most recently happened transactions. Secondly, a multi-level structure learning module is proposed to model the spatial dependency of station-level nodes. It can not only exploit relations between nodes adaptively from data, but also share messages and representations via cluster-level and area-level virtual nodes. Lastly, a cross-level fusion module is designed to integrate multi-level memories and generate comprehensive node representations for the final prediction. Extensive experiments are conducted on two real-world datasets from Beijing Subway and New York Taxi, and the results demonstrate the superiority of our model against the state-of-the-art approaches.

Learning based order dispatching has witnessed tremendous success in ride hailing. However, the success halts within individual ride hailing platforms because sharing raw order dispatching data across platforms may leak user privacy and business secrets. Such data isolation not only impairs user experience but also decreases the potential revenues of the platforms. In this paper, we advocate federated order dispatching for cross-platform ride hailing, where multiple platforms collaboratively make dispatching decisions without sharing their local data. Realizing this concept calls for new federated learning strategies that tackle the unique challenges on effectiveness, privacy and efficiency in the context of order dispatching. In response, we devise Federated Learning-to-Dispatch (Fed-LTD), a framework that allows effective order dispatching by sharing both dispatching models and decisions while providing privacy protection of raw data and high efficiency. We validate Fed-LTD via large-scale trace-driven experiments with Didi GAIA dataset. Extensive evaluations show that Fed-LTD outperforms single-platform order dispatching by 10.24% to 54.07% in terms of total revenue.

Given a sequence of sets with timestamps, where each set includes an arbitrary number of elements, temporal sets prediction aims to predict elements in the consecutive set. Indeed, predicting temporal sets is much more complicated than the conventional predictions of time series and temporal events. Recent studies on temporal sets prediction follow the same pipeline that only learns from each user’s own sequence, which fails to discover the collaborative signals among the sequences of different users. In this paper, we propose a novel element-guided temporal graph neural network to tackle the above issue in temporal sets prediction. Specifically, we first connect sequences of different users via a temporal graph, where nodes contain users and elements, and edges represent user-element interactions with time information. Then, we devise a new message aggregation mechanism to improve the model expressive ability via adaptively learning element-specific representations for each user with the guidance of elements. By performing the element-guided message aggregation among multiple hops, collaborative signals latent in high-order user-element interactions are explicitly encoded. Finally, we present a temporal information utilization module to capture both the semantic and periodic patterns in user sequential behaviors. Experiments on real-world datasets demonstrate that our approach could not only outperform the existing methods with a significant margin but also capture the collaborative signals. Codes and datasets are available at https://github.com/yule-BUAA/ETGNN.

The increasing concerns on data security limit the sharing of data distributedly stored at multiple data owners and impede the scale of spatial queries over big urban data. In response, data federation systems have emerged to perform secure queries across multiple data owners leveraging secure multi-party computation. However, existing systems are designed for relational data. They are highly inefficient on spatial queries and limited in usability. In this demonstration, we introduce Hu-Fu, the first data federation system for secure spatial queries with high efficiency and usability. Hu-Fu is designed from the perspectives of the query user and the data owner for high usability and decomposes a spatial query into as many plaintext operators and as few secure operators as possible for high efficiency. We demonstrate the deployment and usage of Hu-Fu via cross-company taxi-calling, a popular smart city application.

Data isolation has become an obstacle to scale up query processing over big data, since sharing raw data among data owners is often prohibitive due to security concerns. A promising solution is to perform secure queries over a federation of multiple data owners leveraging secure multi-party computation (SMC) techniques, as evidenced by recent federation work over relational data. However, existing solutions are highly inefficient on spatial queries due to excessive secure distance operations for query processing and their usage of general-purpose SMC libraries for secure operation implementation. In this paper, we propose Hu-Fu, the first system for efficient and secure spatial query processing on a data federation. The idea is to decompose the secure processing of a spatial query into as many plaintext operations and as few secure operations as possible, where fewer secure operators are involved and all secure operators are implemented dedicatedly. As a working system, Hu-Fu supports not only query input in native SQL, but also heterogeneous spatial databases ( e.g. , PostGIS, Simba, GeoMesa, and SpatialHadoop) at the backend. Extensive experiments show that Hu-Fu usually outperforms the state-of-the-arts in running time and communication cost while guaranteeing security.

Computing in memory (CIM) is a promising candidate for high throughput and energy-efficient data-driven applications, which mitigates the well-known memory bottleneck in Von Neumann architecture. In this paper, we present a reconfigurable bit-serial operation using toggle spin-orbit torque magnetic random access memory (TSOT-MRAM) to perform the computation completely in the bit-cell array instead of in a peripheral circuit. This bit-serial CIM (BSCIM) scheme achieves higher throughput and energy efficiency in CIM. First, basic Boolean logic operations are realized by utilizing the feature of TSOT device. A bit-cell array that implements the bit-serial operation is then built to provide the communication between column and row necessary for arithmetic operations, such as the carry propagation of addition and multiplication. Finally, we analyze the reliability of BSCIM scheme and demonstrate the performance advantage by performing convolution operations for$28\times 28$handwritten digit images in a BSCIM architecture. The results show that the delay and energy of BSCIM architecture are respectively reduced by 1.16-5.49 times and 1.12-1.43 times compared with the existing digital CIM architectures. Besides, its throughput and energy efficiency are also enhanced to 51.2 GOPS and 9.9 TOPS/W respectively.

Recent years have witnessed the emerging success of Graph Neural Networks (GNNs) for modeling graphical data. A GNN can model the spatial dependencies of nodes in a graph based on message passing through node aggregation. However, in many application scenarios, these spatial dependencies can change over time, and a basic GNN model cannot capture these changes. In this article, we propose a G raph S eq uence neural network with an A tt ention mechanism (GSeqAtt) for processing graph sequences. More specifically, two attention mechanisms are combined: a horizontal mechanism and a vertical mechanism. GTransformer, which is a horizontal attention mechanism for handling time series, is used to capture the correlations between graphs in the input time sequence. The vertical attention mechanism, a Graph Network (GN) block structure with an attention mechanism (GNAtt), acts within the graph structure in each frame of the time series. Experiments show that our proposed model is able to handle information propagation for graph sequences accurately and efficiently. Moreover, results on real-world data from three road intersections show that our GSeqAtt outperforms state-of-the-art baselines on the traffic speed prediction task.

Crowdsensing is an emerging paradigm of ubiquitous sensing, through which a crowd of workers are recruited to perform sensing tasks collaboratively. Although it has stimulated many applications, an open fundamental problem is how to select among a massive number of workers to perform a given sensing task under a limited budget. Nevertheless, due to the proliferation of smart devices equipped with various sensors, it is very difficult to profile the workers in terms of sensing ability. Although the uncertainties of the workers can be addressed by conventional Combinatorial Multi-Armed Bandit (CMAB) framework through a trade-off between exploration and exploitation, we do not have sufficient allowance to directly explore and exploit the workers under the limited budget. Furthermore, since the sensor devices usually have quite limited resources, the workers may have bounded capabilities to perform the sensing task only few times, which further restricts our opportunities to learn the uncertainty. To address the above issues, we propose a Context-Aware Worker Selection (CAWS) algorithm in this paper. By leveraging the correlation between the context information of the workers and their sensing abilities, CAWS aims at maximizing the expected cumulative sensing revenue efficiently with both budget constraint and capacity constraints respected, even when the number of the uncertain workers is massive. The efficacy of CAWS can be verified by rigorous theoretical analysis and extensive experiments.

In knowledge graphs, there are usually different types of nodes, multiple heterogeneous relations, and numerous attributes of nodes and edges, which impose the challenges on the task of Node Importance Estimation (NIE). Indeed, existing NIE approaches, such as PageRank (PR) and Node-Degree (ND), are not designed for handling knowledge graphs with the rich information related with these multifarious nodes and edges. To this end, in this paper, we propose a representation learning framework to leverage the rich information inherent in these multifarious nodes and edges for improving node importance estimation in knowledge graphs. Specifically, we provide a Relational Graph Transformer Network (RGTN), where a relational graph transformer is first proposed to propagate node information with the consideration of semantic predicate representations. Here, the assumption is that different predicates may have distinct effects on the transmission of node importance. Then, two separate encoders are designed to capture both the structural and semantic information of nodes respectively, and a co-attention module is developed to fuse the two separate representations of nodes. Next, an attention-based aggregation module is adopted to map the representations of nodes to their importance values. In addition, a learning-to-rank loss is designed to ensure that the learned representations can be aware of the relative ranking information among nodes. Finally, extensive experiments have been conducted on real-world knowledge graphs, and the results illustrate that our model outperforms the existing methods consistently for all the evaluation metrics. The code and the data are available at https://github.com/GRAPH-0/RGTN-NIE.

Ride hailing is a widespread shared mobility application where the central issue is to assign taxi requests to drivers with various objectives. Despite extensive research on task assignment in ride hailing, the fairness of earnings among drivers is largely neglected. Pioneer studies on fair task assignment in ride hailing are ineffective and inefficient due to their myopic optimization perspective and time-consuming assignment techniques. In this work, we propose LAF, an effective and efficient task assignment scheme that optimizes both utility and fairness. We adopt reinforcement learning to make assignments in a holistic manner and propose a set of acceleration techniques to enable fast fair assignment on large-scale data. Experiments show that LAF outperforms the state-of-the-arts by up to 86.7%, 29.1%, 797% on fairness, utility and efficiency, respectively.

Precise traffic demand prediction could help government and enterprises make better management and operation decisions by providing them with data-driven insights. However, it is a nontrivial effort to design an effective traffic demand prediction method due to the spatial and temporal characteristics of traffic demand distributions, dynamics of human mobility, and impacts of multiple environmental factors. To handle these problems, a Dynamic Transition Convolutional Neural Network (DTCNN) is proposed for the purpose of precise traffic demand prediction. Particularly, a transition network is first constructed according to the citiwide historical departure and arrival records, where the nodes are virtual stations discovered by a density-peak based clustering algorithm and the edges of two nodes correspond to transition flows of two stations. Then, a dynamic transition convolution unit is designed to model the spatial distributions of the traffic demands, and to capture the evolution of the demand dynamics. Last, a unifying learning framework is provided to incorporate the spatiotemporal states of the traffic demands with environmental factors. Experiments have been conducted on NYC taxi and bike-sharing data, and the results validate the effectiveness of the proposed method.

The past decades have witnessed the rise and power of big data, artificial intelligence, the Internet of Things (IoT), cloud computing, and parallel systems. These advanced techniques have great potential and capacity to enable new methodology, applications, and dramatic improvements for current intelligent transportation systems (ITS). To this end, developing new concepts/methodology/tools/algorithms/applications for future ITS with these technologies become more important and promising.

A cost-efficient deal that can achieve high sensing quality with a low reward is the permanent goal of the requestor in mobile crowdsensing, which heavily depends on the quantity and quality of the workers. However, the spatial diversity and temporal dynamics lead to heterogeneous worker supplies, making it hard for the requestor to utilize a homogeneous pricing strategy to realize a cost-efficient deal from a systematic point of view. Therefore, a cost-efficient deal calls for a cost-efficient pricing strategy, boosting the whole sensing quality with less operation (computation) cost. However, the state-of-the-art studies ignore the dual cost-efficient demands of large-scale sensing tasks. Hence, we propose a combinatorial pinning zero-determinant (ZD) strategy, which empowers the requestor to utilize a single strategy within its feasible range to minimize the total expected utilities of the workers throughout all sensing regions for each time interval, without being affected by the strategies of the workers. Through turning the worker-customized strategy to an interval-customized one, the proposed combinatorial pinning ZD strategy reduces the number of pricing strategies required by the requestor from O(n3) to O(n). Besides, it extends the application scenarios of the classical ZD strategy from two-player simultaneous-move games to multiple-heterogeneous-player sequential-move ones, where a leader can determine the linear relationship of the players' expected utilities. Such an extension enriches the theoretical hierarchy of ZD strategies, broadening their application scope. Extensive simulations based on real-world data verify the effectiveness and efficiency of the proposed scheme.

Many applications such as smart metering and location based services pose strong privacy requirements but achieving privacy protection at the client side is a non-trial problem as payment for the services must be computed by the server at the end of each billing period. In this paper, we propose a privacy preservation and billing scheme termed PPDIR based on delayed information release. PPDIR relies on a novel group signature mechanism and the asymmetric Rabin cryptosystem to protect the privacy of the clients and their requests, to achieve accountability and non-repudiation, and to shift the computational complexity to the server side. It adopts a secret token for anonymity and the token is updated for each client at the beginning of each billing period and securely released only to the server at the end of the billing period. Such a strategy can prevent the server from linking a client's requests made at different billing periods. It also prevents any adversary from linking any request to any client. Note that the server is able to figure out all requests made by a client within a billing period after receiving the delayed token, which is unavoidable for billing purpose. We prove the security properties of the group signature scheme, and analyze the security strength of PPDIR. Our study indicates that PPDIR can achieve privacy-preservation, confidentiality, non-repudiation, accountability, and other security objectives. We also evaluate the performance of our scheme in terms of communication and computational overheads.

In this paper, we investigate distributed broadcasting in dynamic networks, where the topology changes continually over time. We propose a network model that captures the dynamicity caused by both churn and mobility of nodes. In contrast to existing work on dynamic networks, our model defines the dynamicity in terms of localized topological changes in the vicinity of each node, rather than a global view of the whole network. Obviously, a local dynamic model suits distributed algorithms better than a global one. The proposed dynamic model uses the more realistic SINR model to depict wireless interference, instead of oversimplified graph-based models adopted in most existing work. We consider the fundamental communication primitive of global broadcast, which is to disseminate a message from a source node to the whole network. Specifically, we present a randomized distributed algorithm that can accomplish dynamic broadcasting in an asymptotically optimal running time of$O(D_{T})$with a high probability guarantee, under the assumption of reasonably constantdynamicity rate, where$D_{T}$is thedynamic diameter, a parameter proposed to depict the complexity of dynamic broadcasting. We believe our local dynamic model can greatly facilitate distributed algorithm studies in mobile and dynamic wireless networks.

In this paper, we present the first algorithm to precisely implement the abstract MAC (absMAC) layer under the physical SINR model in dynamic networks. The absMac layer, first presented by (Kuhn et al., 2009), provides reliable local broadcast communications, with timing guarantees stated in terms of a collection of abstract delay functions, based on which high-level algorithms can be designed, independent of specific channel behaviors. The implementation of absMAC requires the design of a distributed algorithm for the local broadcast communication primitives over a particular communication model that defines concrete channel behaviors, and the objective is to minimize the bounds of the abstract delay functions. Halldórsson et al. (2015) showed that under the standard SINR model (synchronous communications without physical carrier sensing or location information), there exist no efficient exact implementations. In this work, we demonstrate that physical carrier sensing, a commonly seen function performed by wireless devices, can help get efficient exact implementation algorithms. Specifically, we propose an algorithm that precisely implements the absMAC layer under the SINR model in dynamic networks. The algorithm provides asymptotically optimal bounds for both acknowledgement and progress functions defined in the absMAC layer. Our algorithm leads to many new faster algorithms for solving high-level problems under the SINR model in dynamic networks. We demonstrate this by exemplifying problems of Consensus, Multi-Message Broadcast, and Single-Message Broadcast. It deserves to point out that our implementation algorithm is designed based on an optimal algorithm for a General Local Broadcast (GLB) problem, which takes the number of distinct messages into consideration for the first time. The GLB algorithm can handle many communication scenarios apart from those defined in the absMAC layer. Simulation results show that our proposed algorithms perform well in reality.

Given a sequence of sets, where each set contains an arbitrary number of elements, the problem of temporal sets prediction aims to predict the elements in the subsequent set. In practice, temporal sets prediction is much more complex than predictive modelling of temporal events and time series, and is still an open problem. Many possible existing methods, if adapted for the problem of temporal sets prediction, usually follow a two-step strategy by first projecting temporal sets into latent representations and then learning a predictive model with the latent representations. The two-step approach often leads to information loss and unsatisfactory prediction performance. In this paper, we propose an integrated solution based on the deep neural networks for temporal sets prediction. A unique perspective of our approach is to learn element relationship by constructing set-level co-occurrence graph and then perform graph convolutions on the dynamic relationship graphs. Moreover, we design an attention-based module to adaptively learn the temporal dependency of elements and sets. Finally, we provide a gated updating mechanism to find the hidden shared patterns in different sequences and fuse both static and dynamic information to improve the prediction performance. Experiments on real-world data sets demonstrate that our approach can achieve competitive performances even with a portion of the training data and can outperform existing methods with a significant margin.

Many sequential behaviors such as purchasing items from time to time, selecting courses in different terms, collecting event logs periodically could be formalized as sequential sets of actions or elements, namely temporal sets. Predicting the subsequent set according to historical sequence of sets could help us make better producing, scheduling, or operating decisions. However, most of the existing methods were designed for predicting time series or temporal events, which could not be directly used for temporal sets prediction due to the difficulties of multi-level representations of items and sets, complex temporal dependencies of sets, and evolving dynamics of sequential behaviors. To address these issues, this paper provides a novel sets prediction method, called DSNTSP (Dual Sequential Network for Temporal Sets Prediction). Our model first learns both item-level representations and set-level representations of set sequences separately based on a transformer framework. Then, a co-transformer module is proposed to capture the multiple temporal dependencies of items and sets. Last, a gated neural module is designed to predict the subsequent set by fusing all the multi-level correlations and multiple temporal dependencies of items and sets. The experimental results on real-world data sets show that our methods lead to significant and consistent improvements as compared to other methods.

Summary Being part of public transportations, the bike sharing system plays an important role in solving the “last mile” problem. With more advantages than traditional bike sharing systems relying on fixed docks, dockless bike sharing systems are rapidly expanding, which generally operated under cloud‐based architectures. Emerging Things‐Edge‐Cloud (TEC) architectures are showing many advantages than cloud‐based architectures including greater potential in reducing risks of privacy leakage due to their decentralized computing manners. However, even in the TEC architecture, differential attacks, which aims to mine information of individuals in the aggregated data, still cause major threats. To solve this problem, this article proposes a novel encoding and decoding framework within the TEC architecture for time series predictions in bike sharing systems, with considerations of guaranteeing differential privacy. In particular, we first construct a dynamic autoencoder based on the Long Short Term Memory (LSTM) network, then the collected raw temporal data are encoded into a hidden state in the edge end. In the cloud end, the trained output weights are used to reconstruct the current time series and predict the next‐period time series according to received hidden states. This framework not only improves the computation efficiency of bike sharing system by leveraging computing power at the node end but also provides safer data publications that meet the differential privacy requirements. Experiments are conducted on real‐world datasets, results demonstrate the effectiveness of the proposed framework in providing data services with both high utility in sequence predictions and high safety level for users' privacy.

Nodes in wireless sensor networks (WSNs) are usually deployed in an unattended even hostile environment. What is worse, these nodes are equipped with limited battery, storage, computation, and communication resources. Therefore, it is challenging to ensure the security of a WSN without decreasing its network performance. Data aggregation (DA) combined with a security mechanism can provide a good scheme for solving the aforementioned problems. This article presents a comprehensive review of secure DA (SDA) in WSNs, including its security goals together with the existing problems. The traditional network topologies as well as new emerging ones are discussed and compared in order to indicate the application scenes and security levels of different topologies. Meanwhile, the contrastive analyses of security strategies are presented which divides SDA protocols into five categories according to different security mechanisms, security goals, and network topologies. Besides, the discussion points out some open issues which may be the valuable topics of SDA in the future.

This article studies the batch processing of truss maintenance in large graphs. Trussness is a widely used index in graph analytics for cohesive subgraph mining. It is defined on edges to reflect the closeness of vertices connected by the edges. The trussness maintenance problem, i.e., updating trussness after edge insertions/deletions and avoiding recomputation, was proposed by Cohen (2008) with the assumption that real graphs are continuously evolving in nature and their dynamicity usually only affects few edges. Different from the existing work that mainly focuses on simple single edge/vertex insertion/deletion, we propose batch processing algorithms for truss maintenance with multiedge insertions/deletions. By presenting an edge structure called triangle disjoint set, whose insertion/deletion can make each edge change its trussness by at most 1, we tackle the difficulty in quantifying the trussness changes of the edges in batch processing. More specifically, we propose two indices, namely sustain support and pivotal support, to help measure whether the edges have the potential to change their trussness, such that the search range of the potential edges is greatly reduced. The extensive experiments on real-world graphs illustrate that compared with the single-edge processing approach, our batch processing algorithms can significantly improve the processing efficiency, and the improvement becomes more obvious when more edges are inserted/deleted.

Quality control in crowdsourcing is challenging due to the heterogeneous nature of the workers. The state-of-the-art solutions attempt to address the issue from the technical perspective, which may be costly because they function as an additional procedure in crowdsourcing. In this paper, an economics based idea is adopted to embed quality control into the crowdsourcing process, where the requestor can take advantage of the market power to stimulate the workers for submitting high-quality jobs. Specifically, we employ two sequential games to model the interactions between the requestor and the workers, with one considering binary strategies while the other taking continuous strategies. Accordingly, two incentive algorithms for improving the job quality are proposed to tackle the sequential crowdsourcing dilemma problem. Both algorithms are based on a sequential zero-determinant (ZD) strategy modified from the classical ZD strategy. Such a revision not only provides a theoretical basis for designing our incentive algorithms, but also enlarges the application space of the classical ZD strategy itself. Our incentive algorithms have the following desired features: 1) they do not depend on any specific crowdsourcing scenario; 2) they leverage economics theory to train the workers to behave nicely for better job quality instead of filtering out the unprofessional workers; 3) no extra costs are incurred in a long run of crowdsourcing; and 4) fairness is realized as even the requestor (the ZD player), who dominates the game, cannot increase her utility by arbitrarily penalizing any innocent worker.

Peer-to-peer (P2P) services such as mobile P2P transmissions and resource sharing, provide efficient methods to deliver data without the deployment of any central server. Nevertheless, the free-riding phenomenon inherit in such services presses a need for incentive mechanisms to stimulate contributions of data transmissions or sharing. As a result, it is imperative to answer the following questions: whether, and if so to what extent, an incentive mechanism can invoke such contributions? To answerthese questions, we employ an n-player continuous quantum game model to analyze the general extrinsic incentive mechanisms as well as the reputation-based incentive mechanisms, a typical class of extrinsic incentive mechanisms. We focus on studying the extrinsic incentive mechanisms in this paper due to their wide scope of applications stemming from the fact that they promote cooperative behaviors by offering rewards rather than depending on the internal bounds (e.g., social ties) among peers, which may not always exist between any pair of peers. To the best of our knowledge, we are the first to analyze the extrinsic incentive mechanisms for P2P services from a quantum game perspective. Such a perspective is adopted because the extended strategy space in the quantum game broadens the range for searching optimal strategies and the introduction of entanglement makes the proposed analytical frameworks more practical due to the consideration of the peers' relationships imposed by the rewards in extrinsic incentive mechanisms. Our quantum game-based analytical framework is generic because it is compatible with classic game-based schemes. The analytical results can provide a straightforward insight on evaluating the potential of the extrinsic incentive mechanisms and can serve as important references for designing new extrinsic incentive mechanisms.

Link scheduling plays a key role in the network capacity and the transmission delay. In this paper, we study the problem of maximum link scheduling (MLS), aiming to characterize the maximum number of links that can be successfully scheduled simultaneously under Rayleigh-fading and multiuser interference. After analyzing the minimum distance between successful links in the existing GHW scheduling algorithm, we propose a DLS (Distance-based Link Scheduling) algorithm. Then, the global interference is characterized and bounded by introducing a separation distance between selected links, building on which we propose a distributed version of DLS (denoted by DDLS) that converges to a constant factor of the non-fading optimum within time complexity$O(n\ln n)$, where$n$is the number of links. Furthermore, we study the Shortest Link Scheduling (SLS) problem, which minimizes the number of time slots to successfully schedule each link for at least once. An algorithm for SLS with approximation factor of$O(\ln n)$is obtained by executing DDLS. Extensive simulations show that DDLS greatly outperforms GHW and the other two popular algorithms.

The extreme boom of online social networks paves the way for rumor propagation, which may incur an economic loss and cause further public panic. Hence, there is a pressing need to develop countermeasures for reducing side effects posed by rumors. Different from the state-of-the-art work that mostly conducted micro-perspective studies, our paper focuses on a macro-perspective one. In detail, our study neglects technical details and analyzes the antagonistic dynamics between the rumormonger and the rumor suppressor, which provides a deep understanding of the overall development trend of rumor propagation. To reveal the potentials of the rumormonger and the rumor suppressor, the competence-oriented analysis is proposed, where the sufficient and necessary conditions for the existence of the Nash equilibrium in this rumor game are proved rigorously, helping us to derive steady ratios of people who trust or deny a rumor. To figure out the optimal strategy to strike back the rumormonger, the target-oriented analysis is conducted, in which the analytical solutions when the strategies of both players are static are solved and an iteration algorithm is employed to obtain the numerical solutions when their strategies are dynamic. Both numerical and real-world-data based simulations are adopted to verify the proposed competence-oriented and target-oriented analyses.

We study the fundamental problem of fault-tolerant distributed sampling towards uniform probabilistic distribution in dynamic multi-hop wireless networks. Whereas uniform sampling has been extensively studied without concerning fault tolerance, only quite few proposals investigate how the uniform sampling algorithm tolerate Byzantine faults on dynamic networks with very special topologies, e.g., regular graphs with constant node degree. Therefore, designing fault-tolerant uniform sampling algorithms for more general graphs is still an open problem. To this end, we propose a fast and highly fault-tolerate randomized algorithm, such that nearly-uniform sampling is achieved in O(log2n) rounds, while up to O(√n/(polylog(n)·Δ)) Byzantine nodes can be tolerated, where Δ is the maximum degree of the network. Moreover, the proposed algorithm is also communication efficient in the sense that only O(log n) bits need to be exchanged on each link in every round. To show the power of distributed uniform sampling, we apply the proposed algorithm in designing polylogarithmic time distributed algorithms for two typical fundamental issues, i.e., to achieve agreement or data aggregation in Byzantine dynamic networks.

A crowdsourcing task in real-world applications often consists of thousands of atomic tasks. A common practice to distribute a large-scale crowdsourcing task is to pack atomic tasks into task bins and send to crowd workers in batches. It is challenging to decompose a large-scale crowdsourcing task into task bins to ensure reliability at a minimal total cost. In this paper, we propose the Smart Large-scAle task DEcomposer (SLADE) problem, which aims to decompose a large-scale crowdsourcing task to achieve the desired reliability at a minimal cost. We prove its NP-hardness and study two variants of the problem. For the homogeneous SLADE problem, we propose a greedy algorithm and an approximation framework using an optimal priority queue (OPQ) structure with provable approximation ratio. For the heterogeneous SLADE problem, we extend this framework and prove its approximation guarantee. Extensive experiments validate the effectiveness and efficiency of the solutions.

Online bipartite graph matching is attracting growing research attention due to the development of dynamic task assignment in sharing economy applications, where tasks need be assigned dynamically to workers. Past studies lack practicability in terms of both problem formulation and solution framework. On the one hand, some problem settings in prior online bipartite graph matching research are impractical for real-world applications. On the other hand, existing solutions to online bipartite graph matching are inefficient due to the unnecessary real-time decision making. In this paper, we propose the dynamic bipartite graph matching (DBGM) problem to be better aligned with real-world applications and devise a novel adaptive batch-based solution framework with a constant competitive ratio. As an effective and efficient implementation of the solution framework, we design a reinforcement learning based algorithm, called Restricted Q-learning (RQL), which makes near-optimal decisions on batch splitting. Extensive experimental results on both real and synthetic datasets show that our methods outperform the state-of-the-arts in terms of both effectiveness and efficiency.

Multi-task learning is a successful machine learning framework which improves the performance of prediction models by leveraging knowledge among tasks, e.g., the relationships between different tasks. Most of existing multi-task learning methods focus on guiding learning process by predefined task relationships. In fact, these methods have not fully exploited the associated relationships during the learning process. On the one hand, replacing predefined task relationships by adaptively learned ones may result in higher prediction accuracy as it can avoid the risk of misguiding caused by improperly predefined relationships. On the other hand, apart from the task relationships, feature-task dependence and feature-feature interactions could also be employed to guide the learning process. Along this line, we propose aMultiple Relational Attention Network (MRAN) framework for multi-task learning, in which three types of relationships are considered. Correspondingly, MRAN consists of three attention-based relationship learning modules: 1) a task-task relationship learning module which captures the relationships among tasks automatically and controls the positive and negative knowledge transfer adaptively; 2) a feature-feature interaction learning module that handles the complicated interactions among features; 3) a task-feature dependence learning module, which can associate the related features with target tasks separately. To evaluate the effectiveness of the proposed MARN, experiments are conducted on two public datasets and a real-world dataset crawled from a review hosting site. Experimental results demonstrate the superiority of our method over both classical and the state-of-the-art multi-task learning methods.

The rapid developments of the Internet of Things (IoT) and smart mobile devices in recent years have been dramatically incentivizing the advancement of edge computing. On the one hand, edge computing has provided a great assistance for lightweight devices to accomplish complicated tasks in an efficient way; on the other hand, its hasty development leads to the neglection of security threats to a large extent in edge computing platforms and their enabled applications. In this paper, we provide a comprehensive survey on the most influential and basic attacks as well as the corresponding defense mechanisms that have edge computing specific characteristics and can be practically applied to real-world edge computing systems. More specifically, we focus on the following four types of attacks that account for 82% of the edge computing attacks recently reported by Statista: distributed denial of service attacks, side-channel attacks, malware injection attacks, and authentication and authorization attacks. We also analyze the root causes of these attacks, present the status quo and grand challenges in edge computing security, and propose future research directions.

Predicting the passenger flow of public transport in a newly developed area of a city is very urgent for designing a precise and efficient public transport network. This paper proposes a new prediction model by exploring the relationship between the passenger flow of a station and its surrounding area's factors. First, in order to obtain more accurate factors affecting the passenger flow, the city is divided into multiple regions with similar internal traffic properties and moderate spatial size using the data of urban road network and buildings. Second, to effectively solve the problem of fuzziness of the station's attraction scope, the concept of the membership degree and fuzzy processing method is proposed. Finally, the station's passenger flow prediction model is launched based on Xgboost. The experimental results on three districts in Beijing show that our method outperforms all baselines significantly, which improves the accuracy by more than 20%.

In this paper, we present a novel approach to machine reading comprehension for the MS-MARCO dataset. Unlike the SQuAD dataset that aims to answer a question with exact text spans in a passage, the MS-MARCO dataset defines the task as answering a question from multiple passages and the words in the answer are not necessary in the passages. We therefore develop an extraction-then-synthesis framework to synthesize answers from extraction results. Specifically, the answer extraction model is first employed to predict the most important sub-spans from the passage as evidence, and the answer synthesis model takes the evidence as additional features along with the question and passage to further elaborate the final answers. We build the answer extraction model with state-of-the-art neural networks for single passage reading comprehension, and propose an additional task of passage ranking to help answer extraction in multiple passages. The answer synthesis model is based on the sequence-to-sequence neural networks with extracted evidences as features. Experiments show that our extraction-then-synthesis method outperforms state-of-the-art methods.

Modeling sentence pairs plays the vital role for judging the relationship between two sentences, such as paraphrase identification, natural language inference, and answer sentence selection. Previous work achieves very promising results using neural networks with attention mechanism. In this paper, we propose the multiway attention networks which employ multiple attention functions to match sentence pairs under the matching-aggregation framework. Specifically, we design four attention functions to match words in corresponding sentences. Then, we aggregate the matching information from each function, and combine the information from all functions to obtain the final representation. Experimental results demonstrate that the proposed multiway attention networks improve the result on the Quora Question Pairs, SNLI, MultiNLI, and answer sentence selection task on the SQuAD dataset.

In this paper, we study the task of reading comprehension style answer sentence selection that aims to select the best sentence from a given passage to answer a question. Unlike most previous works that match the question and each candidate sentence separately, we observe that the context information among sentences in the same passage plays a vital role in this task. We propose modeling context information with hierarchical gated recurrent neural networks. Specifically, we first apply a word level recurrent neural network to model the context independent matching between the question and each candidate sentence. We then employ a sentence level recurrent neural network to incorporate the context information among all candidate sentences. Moreover, we introduce the gate mechanism to select matching information before feeding into recurrent neural networks at both word and sentence level. Experiments on the WikiQA and SQuAD datasets show that our model outperforms state-of-the-art methods.

Crowdsourcing has been shown to be effective in a wide range of applications, and is seeing increasing use. A large-scale crowdsourcing task often consists of thousands or millions of atomic tasks, each of which is usually a simple task such as binary choice or simple voting. To distribute a large-scale crowdsourcing task to limited crowd workers, a common practice is to pack a set of atomic tasks into a task bin and send to a crowd worker in a batch. It is challenging to decompose a large-scale crowdsourcing task and execute batches of atomic tasks, which ensures reliable answers at a minimal total cost. Large batches lead to unreliable answers of atomic tasks, while small batches incur unnecessary cost. In this paper, we investigate a general crowdsourcing task decomposition problem, called the Smart Large-scAle task DEcomposer (SLADE) problem, which aims to decompose a large-scale crowdsourcing task to achieve the desired reliability at a minimal cost. We prove the NP-hardness of the SLADE problem and propose solutions in both homogeneous and heterogeneous scenarios. For the homogeneous SLADE problem, where all the atomic tasks share the same reliability requirement, we propose a greedy heuristic algorithm and an efficient and effective approximation framework using an optimal priority queue (OPQ) structure with provable approximation ratio. For the heterogeneous SLADE problem, where the atomic tasks can have different reliability requirements, we extend the OPQ-based framework leveraging a partition strategy, and also prove its approximation guarantee. Finally, we verify the effectiveness and efficiency of the proposed solutions through extensive experiments on representative crowdsourcing platforms.

We present a simple yet effective approach for linking entities in queries.The key idea is to search sentences similar to a query from Wikipedia articles and directly use the human-annotated entities in the similar sentences as candidate entities for the query.Then, we employ a rich set of features, such as link-probability, contextmatching, word embeddings, and relatedness among candidate entities as well as their related entities, to rank the candidates under a regression based framework.The advantages of our approach lie in two aspects, which contribute to the ranking process and final linking result.First, it can greatly reduce the number of candidate entities by filtering out irrelevant entities with the words in the query.Second, we can obtain the query sensitive prior probability in addition to the static linkprobability derived from all Wikipedia articles.We conduct experiments on two benchmark datasets on entity linking for queries, namely the ERD14 dataset and the GERDAQ dataset.Experimental results show that our method outperforms state-of-the-art systems and yields 75.0% in F1 on the ERD14 dataset and 56.9% on the GERDAQ dataset.

Taxi-calling apps are gaining increasing popularity for their efficiency in dispatching idle taxis to passengers in need. To precisely balance the supply and the demand of taxis, online taxicab platforms need to predict the Unit Original Taxi Demand (UOTD), which refers to the number of taxi-calling requirements submitted per unit time (e.g., every hour) and per unit region (e.g., each POI). Predicting UOTD is non-trivial for large-scale industrial online taxicab platforms because both accuracy and flexibility are essential. Complex non-linear models such as GBRT and deep learning are generally accurate, yet require labor-intensive model redesign after scenario changes (e.g., extra constraints due to new regulations). To accurately predict UOTD while remaining flexible to scenario changes, we propose LinUOTD, a unified linear regression model with more than 200 million dimensions of features. The simple model structure eliminates the need of repeated model redesign, while the high-dimensional features contribute to accurate UOTD prediction. We further design a series of optimization techniques for efficient model training and updating. Evaluations on two large-scale datasets from an industrial online taxicab platform verify that LinUOTD outperforms popular non-linear models in accuracy. We envision our experiences to adopt simple linear models with high-dimensional features in UOTD prediction as a pilot study and can shed insights upon other industrial large-scale spatio-temporal prediction problems.

Recently, crowdsourcing platforms have attracted a number of citizens to perform a variety of location-specific tasks. However, most existing approaches consider the arrangement of a set of tasks for a set of crowd workers, while few consider crowd workers arriving in a dynamic manner. Therefore, how to arrange suitable location-specific tasks to a set of crowd workers such that the crowd workers obtain maximum satisfaction when arriving sequentially represents a challenge. To address the limitation of existing approaches, we first identify a more general and useful model that considers not only the arrangement of a set of tasks to a set of crowd workers, but also all the dynamic arrivals of all crowd workers. Then, we present an effective crowd-task model which is applied to offline and online settings, respectively. To solve the problem in an offline setting, we first observe the characteristics of task planning (CTP) and devise a CTP algorithm to solve the problem. We also propose an effective greedy method and integrated simulated annealing (ISA) techniques to improve the algorithm performance. To solve the problem in an online setting, we develop a greedy algorithm for task planning. Finally, we verify the effectiveness and efficiency of the proposed solutions through extensive experiments using real and synthetic datasets.

With the rapid increase of leakage currents, non-volatile memories have become competitive candidates in the next-generation computer architecture. Among them, STT-MRAM shows great promise in working memory with high density, high speed and tremendous endurance, etc. However, based on our investigations, the dynamic write power and read reliability are two critical challenges of STT-MRAM. In this work, we propose a synergistic pseudo-differential sensing (PDS) framework that employs device, circuit and architectural techniques to address these challenges. In specific, three design techniques, including cell cluster, asymmetric sensing amplifier and self-error-detection-correction, are proposed to implement the PDS framework. We show that the holistic device-circuit-architecture cross-layer co-design enables STT-MRAM to be utilized in the cache memory, benefiting from the improved density, reliability and energy-efficiency. Our experimental results show that the proposed PDS scheme improves the read margin by ~35.6 percent, reduces the area, read latency, read energy, write latency and write power by ~46.7, ~9.8, ~30.3, ~2.3 and ~31.1 percent respectively, compared with the typical 1T1MTJ cell structure for the cache capacity of 8 MB. In addition, the proposed PDS scheme reduces the dynamic energy by ~32.9 percent and leakage energy by ~830 percent, improves the IPC by ~1.3 percent and miss rate by ~36.9 percent respectively, compared with conventional SRAM based cache.

STT-MRAM has been considered as one of the most promising nonvolatile memory candidates in the next-generation of computer architecture. However, the read reliability and dynamic write power concerns greatly hinder its practical application. In this paper, we propose a synergistic solution, namely pseudo-differential sensing (PDS), to jointly address these two concerns. Three techniques, including cell cluster, asymmetric sensing amplifier (ASA) and self-error-detection-correction (SEDC), are proposed to implement the PDS concept. Our experimental results show that the PDS scheme with the 3T3MTJ cell cluster can reduce the area (~21.7%) and write power (~25.6%) of the differential sensing (DS) scheme while improve the read reliability (read margin, ~35.6%) of the typical sensing (TS) scheme for a 16 Mbit cache. Furthermore, the PDS scheme with the 1T3MTJ cell cluster can outperform both the TS and DS schemes in terms of area (~40.0%, ~66.1%), read latency (~16.6%, ~32.1%), read power (~16.7%, ~37.1%), write latency (~5.4%, 16.3%) and write power (~18.6%, ~43.4%).

Chinese character riddle is a riddle game in which the riddle solution is a single Chinese character.It is closely connected with the shape, pronunciation or meaning of Chinese characters.The riddle description (sentence) is usually composed of phrases with rich linguistic phenomena (such as pun, simile, and metaphor), which are associated to different parts (namely radicals) of the solution character.In this paper, we propose a statistical framework to solve and generate Chinese character riddles.Specifically, we learn the alignments and rules to identify the metaphors between phrases in riddles and radicals in characters.Then, in the solving phase, we utilize a dynamic programming method to combine the identified metaphors to obtain candidate solutions.In the riddle generation phase, we use a template-based method and a replacement-based method to obtain candidate riddle descriptions.We then use Ranking SVM to rerank the candidates both in the solving and generation process.Experimental results in the solving task show that the proposed method outperforms baseline methods.We also get very promising results in the generation task according to human judges.

Transport infrastructure generates a huge amount of city transportation data due to the significant increasing of advanced devices, such as sensing devices, mobile devices and real-time monitors. However, transportation big data cannot be fully analyzed and utilized by urban traffic data services currently. This paper proposes a novel City Traffic Data-as-a-Service (CTDaaS), which fuses data from distributed providers. Initially, we build an Internet of Traffic Data Service (IoTDS) model to identify associations and relationships among data resources. Then a CTDaaS agent is developed under Transparent Computing paradigm and service oriented architecture. It receives user requests, fuses knowledge from a variety of data sources according to different computing models, and responses differentiated Quality of Data (QoD). Finally, an application scenario, named Park and Ride (P+R), is implemented and evaluated to demonstrate how the service works using existing dynamic city traffic data.

Much work has been done on feature selection. Existing methods are based on document frequency, such as Chi-Square Statistic, Information Gain etc. However, these methods have two shortcomings: one is that they are not reliable for low-frequency terms, and the other is that they only count whether one term occurs in a document and ignore the term frequency. Actually, high-frequency terms within a specific category are often regards as discriminators. This paper focuses on how to construct the feature selection function based on term frequency, and proposes a new approach based on t-test, which is used to measure the diversity of the distributions of a term between the specific category and the entire corpus. Extensive comparative experiments on two text corpora using three classifiers show that our new approach is comparable to or or slightly better than the state-of-the-art feature selection methods (i.e., chi2, and IG) in terms of macro-F1 and micro-F1

In Delay Tolerant Networks (DTNs), characteristics of mobility model have essential impact on routing protocols design and verification. Most of current studies about network characteristics are derived from theoretical models or small-scale real network traces. Properties of nodes in those networks are simple and can not reflect features in large-scale applications. In addition, few studies focus on modeling large-scale urban DTNs based on the network characteristics. In this paper, we analyze a large-scale urban DTN including traces from 12096 taxies in Beijing City. We observed that inter contact time (ICT) between two nodes satisfies exponential distribution, and the network forms a number of hotspot areas in which the vehicles tend to cluster. Based on the observation, we design a DTN mobility model by introducing characteristics of hotspot area and prove that distribution of ICT in this model also exhibits exponential nature as it is in real urban DTNs. Our further simulation experiment reveals the similarity between the proposed model and urban DTNs. This result thus demonstrates that the model is rational to guide DTN protocols design and verification in large-scale applications.

A set of distributed continual range query requests, each defining a geographical region of interest, needs to be periodically reevaluated to provide up to date answers. Processing these continual queries efficiently and incrementally becomes important for location based services and applications. In this paper, we propose an efficient incremental method for continuous range query characterized by mobility of objects which follow paths in an underlying spatial road network. We notice that both queries and moving objects can be attached to the road link for updating of query answers. By using Grid R∗-tree which indexing spatial road network data, query requests and moving objects register themselves to corresponding road links according to query areas and moving object locations on the network. Also we analyzed the impacts to query answers caused by geometry relation of road link and query area and state of moving objects. Then we proposed an efficient update algorithm and corresponding memory data structures based on spatial and state classification which formed a safe region to avoid unnecessary updates. Finally a comprehensive experimental evaluation using real data has been conducted to demonstrate the efficiency and effectiveness of our algorithm.

Nowadays Float Car Data (FCD) is playing an important role in real-time traffic information systems. However, traffic signal control in urban road network will cause random delay on float cars, and this kind of delay will result in considerable fluctuation of travel time. Thus, the accuracy of FCD system is seriously affected. In this paper, float car refining models are proposed to calculate the stopped-time delay by means of low-sampling-rate FCD. And then, the classification of controlled delay and non-controlled delay is performed in order to remove traffic signal control's affection, and to obtain the data which can truly reflect the traffic flow characteristics. The contrast experiments indicate that the accuracy of the FCD system has achieved significant improvement after applying the new processing model.

Since media data in streaming media system are high volume and latency sensitive, transmission security of them have been a challenge task. To solve the problem, partial encryption and other media encryption schemes have been proposed. However those schemes are tradeoffs between security and efficiency. In a multi-stream system, using one media encryption scheme to protect all the media streams will induce either unscalability or insecurity. In this paper, the idea of partial encryption is generalized from encrypting a subset of one stream to multi-streams. A mathematical model based dynamic optimal selective control mechanism for multi-datastream security is proposed. Since the simplified model is 0-1 knapsack problem, which is NP-hard, a greedy heuristic incremental approximate algorithm is designed. Theoretical and experimental analyses show the performance of the algorithm is effective enough to support real-time applications. A prototype has been implemented in our Admire system, and used in a confidential project.

The SID (shared information/data) model, which is the definition of business entities involved in telecommunication operations management, plays an important role in enabling NGOSS (new generation operations support system) integration and interoperability. TeleManagement Forum's current work on refining the SID model is based on UML metamodel. However, merely such a definition in UML is not sufficient to satisfy various demands for SID across the whole NGOSS lifecycle. In this research, we introduce the SOBDL (SID Ontology Based on Description Logics), a description logic based knowledge representation system, to provide a set of querying and reasoning services for SID requirements in NGOSS from design-time to run-time. In the paper, we describe the SOBDL in detail from various aspects such as architecture, inference services, and role in NGOSS integration. We also discuss the SOBDL languages intensively and give an example of SOBDL in OWL (Web ontology language). In the end, we draw a conclusion and introduce our future research.

Future wireless must be able to integrate most different heterogeneous IP-based networks and supply the user coordinate service without a broken connection within a diverse and overlay access network environment. One of the most challenges of wireless network integration is handover decision. To select the best network considering various network attributes, we present a network evaluation method (NEM) as a genetic criterion with user preference and usual estimation standards. With NEM, our handover decision can support not only vertical handover, also horizontal handover meanwhile by comparing cells available in current network. Furthermore, we propose a new prediction algorithm (DGRAD) to predict monitoring values of each factor prior to handover execution phase which addresses more accurate input parameters into NEM junctions and provide reasonable final handover suggestions for users

Alarm correlation plays an important role in improving the service and reliability in modern telecommunication networks. Most previous research of alarm correlation did not consider the effects of noise data in the database. This paper focuses on the method of discovering alarm correlation rules from a database containing noise data. We firstly define two parameters, win-freq and win-add, as the measures of noise data and then present a robust search algorithm to solve the problem. At different size of win-freq and win-add, the experiments on the alarm database containing noise data show that the robust search algorithm can discover more rules with the bigger size of win-add. We also compare, by experiments, two different interestingness measures of confidence and correlation.