Publications (42)
Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learning
Ruobing Jiang, Yacong Li, Haobing Liu +1
Heterogeneous graphs (HGs) are composed of multiple types of nodes and edges, making it more effective in capturing the complex relational structures inherent in the real world. Ho…
Enhancing Underwater Images via Adaptive Semantic-aware Codebook Learning
Bosen Lin, Feng Gao, Yanwei Yu +2
Underwater Image Enhancement (UIE) is an ill-posed problem where natural clean references are not available, and the degradation levels vary significantly across semantic regions.…
TPAoI: Ensuring Fresh Service Status at the Network Edge in Compute-First Networking
Haosheng He, Jianpeng Qi, Chao Liu +2
In compute-first networking, maintaining fresh and accurate status information at the network edge is crucial for effective access to remote services. This process typically involv…
Unlocking air traffic flow prediction through microscopic aircraft-state modeling
Bin Wang, Anqi Liu, Jiangtao Zhao +8
Short-term air traffic flow prediction in terminal airspace is essential for proactive air traffic management. Existing approaches predominantly model traffic flow as aggregated ti…
Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text Kernel
Zhihao Wang, Yanwei Yu, Yibo Wang +2
Offline Chinese handwriting text recognition is a long-standing research topic in the field of pattern recognition. In previous studies, text detection and recognition are separate…
Hierarchy-Consistent Learning and Adaptive Loss Balancing for Hierarchical Multi-Label Classification
Ruobing Jiang, Mengzhe Liu, Haobing Liu +1
Hierarchical Multi-Label Classification (HMC) faces critical challenges in maintaining structural consistency and balancing loss weighting in Multi-Task Learning (MTL). In order to…
Machine Learning for Depression Screening and Intervention: an Original Circadian Rhythm Score-based Methodology
Bin Wang, Shuo Lian, Yuanyuan Hou +5
Depression screening from large-scale behavioral data is challenged by fragmented circadian indicators, limited interpretability, and the lack of intervention-oriented analysis. Ex…
Multi-Channel Hypergraph Contrastive Learning for Matrix Completion
Xiang Li, Changsheng Shui, Zhongying Zhao +2
Rating is a typical user explicit feedback that visually reflects how much a user likes a related item. The (rating) matrix completion is essentially a rating prediction process, w…
FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction
Kunyu Ni, Lei Cao, Jie He +4
Data preparation pipelines improve data quality in machine learning by transforming raw tables into learning-ready data through sequential cleaning and feature transformation opera…
A Survey on Open-Source Edge Computing Simulators and Emulators: The Computing and Networking Convergence Perspective
Jianpeng Qi, Chao Liu, Xiao Zhang +4
Edge computing, with its low latency, dynamic scalability, and location awareness, along with the convergence of computing and communication paradigms, has been successfully applie…
Trajectory-User Linking via Hierarchical Spatio-Temporal Attention Networks
Wei Chen, Chao Huang, Yanwei Yu +2
Trajectory-User Linking (TUL) is crucial for human mobility modeling by linking diferent trajectories to users with the exploration of complex mobility patterns. Existing works mai…
Self-supervised Scene Text Segmentation with Object-centric Layered Representations Augmented by Text Regions
Yibo Wang, Yunhu Ye, Yuanpeng Mao +2
Text segmentation tasks have a very wide range of application values, such as image editing, style transfer, watermark removal, etc.However, existing public datasets are of poor qu…
Mutual Distillation Learning Network for Trajectory-User Linking
Wei Chen, Shuzhe Li, Chao Huang +3
Trajectory-User Linking (TUL), which links trajectories to users who generate them, has been a challenging problem due to the sparsity in check-in mobility data. Existing methods i…
Non-collective Calibrating Strategy for Time Series Forecasting
Bin Wang, Yongqi Han, Minbo Ma +4
Deep learning-based approaches have demonstrated significant advancements in time series forecasting. Despite these ongoing developments, the complex dynamics of time series make i…
Structure-Aware Automatic Channel Pruning by Searching with Graph Embedding
Zifan Liu, Yuan Cao, Yanwei Yu +2
Channel pruning is a powerful technique to reduce the computational overhead of deep neural networks, enabling efficient deployment on resource-constrained devices. However, existi…
Scalable Trajectory-User Linking with Dual-Stream Representation Networks
Hao Zhang, Wei Chen, Xingyu Zhao +3
Trajectory-user linking (TUL) aims to match anonymous trajectories to the most likely users who generated them, offering benefits for a wide range of real-world spatio-temporal app…
Correlation-Attention Masked Temporal Transformer for User Identity Linkage Using Heterogeneous Mobility Data
Ziang Yan, Xingyu Zhao, Hanqing Ma +4
With the rise of social media and Location-Based Social Networks (LBSN), check-in data across platforms has become crucial for User Identity Linkage (UIL). These data not only reve…
Scalable Motif Counting for Large-scale Temporal Graphs
Zhongqiang Gao, Chuanqi Cheng, Yanwei Yu +3
One fundamental problem in temporal graph analysis is to count the occurrences of small connected subgraph patterns (i.e., motifs), which benefits a broad range of real-world appli…
Decision-Aware Semantic State Synchronization in Compute-First Networking
Jianpeng Qi, Chao Liu, Chengrui Wang +3
In Compute-First Networking (CFN), an Access Point (AP) makes task offloading decisions based on resource state information reported by a Service Node (SN). A fundamental challenge…
From Time Series to State: Situation-Aware Modeling for Air Traffic Flow Prediction
Anqi Liu, Jiangtao Zhao, Guiyuan Jiang +3
Accurate air traffic prediction in the terminal airspace (TA) is pivotal for proactive air traffic management (ATM). However, existing data-driven approaches predominantly rely on…
Efficient Discovery of Motif Transition Process for Large-Scale Temporal Graphs
Zhiyuan Zheng, Jianpeng Qi, Jiantao Li +3
Understanding the dynamic transition of motifs in temporal graphs is essential for revealing how graph structures evolve over time, identifying critical patterns, and predicting fu…
Exploring the Tradeoff Between Diversity and Discrimination for Continuous Category Discovery
Ruobing Jiang, Yang Liu, Haobing Liu +2
Continuous category discovery (CCD) aims to automatically discover novel categories in continuously arriving unlabeled data. This is a challenging problem considering that there is…
Efficient Information Updates in Compute-First Networking via Reinforcement Learning with Joint AoI and VoI
Jianpeng Qi, Chao Liu, Chengxiang Xu +3
Timely and efficient dissemination of service information is critical in compute-first networking systems, where user requests arrive dynamically and computing resources are constr…
Downstream Task Inspired Underwater Image Enhancement: A Perception-Aware Study from Dataset Construction to Network Design
Bosen Lin, Feng Gao, Yanwei Yu +2
In real underwater environments, downstream image recognition tasks such as semantic segmentation and object detection often face challenges posed by problems like blurring and col…
Closed-Form and Boundary Expressions for Task-Success Probability in Status-Driven Systems
Jianpeng Qi, Chao Liu, Rui Wang +2
Timely and efficient dissemination of server status is critical in compute-first networking systems, where user tasks arrive dynamically and computing resources are limited and sto…
UMGAD: Unsupervised Multiplex Graph Anomaly Detection
Xiang Li, Jianpeng Qi, Zhongying Zhao +4
Graph anomaly detection (GAD) is a critical task in graph machine learning, with the primary objective of identifying anomalous nodes that deviate significantly from the majority.…
Dual-Channel Multiplex Graph Neural Networks for Recommendation
Xiang Li, Chaofan Fu, Zhongying Zhao +4
Effective recommender systems play a crucial role in accurately capturing user and item attributes that mirror individual preferences. Some existing recommendation techniques have…
Dataset Condensation for Time Series Classification via Dual Domain Matching
Zhanyu Liu, Ke Hao, Guanjie Zheng +1
Time series data has been demonstrated to be crucial in various research fields. The management of large quantities of time series data presents challenges in terms of deep learnin…
Multiplex Heterogeneous Graph Convolutional Network
Pengyang Yu, Chaofan Fu, Yanwei Yu +3
Heterogeneous graph convolutional networks have gained great popularity in tackling various network analytical tasks on heterogeneous network data, ranging from link prediction to…
Lightweight yet Fine-grained: A Graph Capsule Convolutional Network with Subspace Alignment for Shared-account Sequential Recommendation
Jinyu Zhang, Zhongying Zhao, Chao Li +1
Shared-account Sequential Recommendation (SSR) aims to provide personalized recommendations for accounts shared by multiple users with varying sequential preferences. Previous stud…
AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning
Lixian Jing, Jianpeng Qi, Junyu Dong +1
As deep neural networks (DNNs) are increasingly deployed on edge devices, optimizing models for constrained computational resources is critical. Existing auto-pruning methods face…
Spatiotemporal-aware Trend-Seasonality Decomposition Network for Traffic Flow Forecasting
Lingxiao Cao, Bin Wang, Guiyuan Jiang +2
Traffic prediction is critical for optimizing travel scheduling and enhancing public safety, yet the complex spatial and temporal dynamics within traffic data present significant c…
Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation
Yuhao Yang, Chao Huang, Lianghao Xia +3
Learning dynamic user preference has become an increasingly important component for many online platforms (e.g., video-sharing sites, e-commerce systems) to make sequential recomme…
Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bank
Zhanyu Liu, Guanjie Zheng, Yanwei Yu
Traffic forecasting is a critical service in Intelligent Transportation Systems (ITS). Utilizing deep models to tackle this task relies heavily on data from traffic sensors or vehi…
Weighted Graph Clustering via Scale Contraction and Graph Structure Learning
Haobing Liu, Yinuo Zhang, Tingting Wang +2
Graph clustering aims to partition nodes into distinct clusters based on their similarity, thereby revealing relationships among nodes. Nevertheless, most existing methods do not f…
TrajDiff: Diffusion Bridge Network with Semantic Alignment for Trajectory Similarity Computation
Xiao Zhang, Xingyu Zhao, Hong Xia +4
With the proliferation of location-tracking technologies, massive volumes of trajectory data are continuously being collected. As a fundamental task in trajectory data mining, traj…
ShapeCond: Fast Shapelet-Guided Dataset Condensation for Time Series Classification
Sijia Peng, Yun Xiong, Xi Chen +5
Time series data supports many domains (e.g., finance and climate science), but its rapid growth strains storage and computation. Dataset condensation can alleviate this by synthes…
Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference
Xianfeng Tang, Boqing Gong, Yanwei Yu +4
Real-time traffic volume inference is key to an intelligent city. It is a challenging task because accurate traffic volumes on the roads can only be measured at certain locations w…
Online Discovery of Evolving Groups over Massive-Scale Trajectory Streams
Yanwei Yu, Ruoshan Lan, Lei Cao +2
The increasing pervasiveness of object tracking technologies leads to huge volumes of spatiotemporal data collected in the form of trajectory streams. The discovery of useful group…
Trajectory Data Management and Mining: A Survey from Deep Learning to the LLM Era
Wei Chen, Yuanshao Zhu, Yanchuan Chang +11
Trajectory computing is a pivotal domain encompassing trajectory data management and mining, garnering widespread attention due to its crucial role in various practical application…
ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion
Xiang Li, Jianpeng Qi, Haobing Liu +6
Graph Neural Networks (GNNs) have demonstrated impressive performance across diverse graph-based tasks by leveraging message passing to capture complex node relationships. However,…
Multi-scale Traffic Pattern Bank for Cross-city Few-shot Traffic Forecasting
Zhanyu Liu, Guanjie Zheng, Yanwei Yu
Traffic forecasting is crucial for intelligent transportation systems (ITS), aiding in efficient resource allocation and effective traffic control. However, its effectiveness often…