460 citations · 646 across the 18 of their papers we have counts for
18 papers
KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU
Di Chai, Leye Wang, Zeshen Su +2
Modern LLM agents operate in persistent workspaces whose accumulated history can exceed both GPU KV capacity and the model's native context window. Existing systems typically compa…
Learning-based Privacy-Preserving Graph Publishing Against Sensitive Link Inference Attacks
Yucheng Wu, Yuncong Yang, Xiao Han +2
Publishing graph data is widely desired to enable a variety of structural analyses and downstream tasks. However, it also potentially poses severe privacy leakage, as attackers may…
ChatPD: An LLM-driven Paper-Dataset Networking System
Anjie Xu, Ruiqing Ding, Leye Wang
Scientific research heavily depends on suitable datasets for method validation, but existing academic platforms with dataset management like PapersWithCode suffer from inefficienci…
WiCross: Indoor Human Zone-Crossing Detection Using Commodity WiFi Devices
Weiyan Shi, Xuanzhi Wang, Kai Niu +2
Detecting whether a target crosses the given zone (e.g., a door) can enable various practical applications in smart homes, including intelligent security and people counting. The t…
Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data
Ji Liu, Juncheng Jia, Hong Zhang +5
Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this pape…
A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability
Jie Zhu, Jirong Zha, Ding Li +1
Self-supervised learning shows promise in harnessing extensive unlabeled data, but it also confronts significant privacy concerns, especially in vision. In this paper, we aim to pe…
Graph Contrastive Learning with Cohesive Subgraph Awareness
Yucheng Wu, Leye Wang, Xiao Han +1
Graph contrastive learning (GCL) has emerged as a state-of-the-art strategy for learning representations of diverse graphs including social and biomedical networks. GCL widely uses…
Knowledge-inspired Subdomain Adaptation for Cross-Domain Knowledge Transfer
Liyue Chen, Linian Wang, Jinyu Xu +5
Most state-of-the-art deep domain adaptation techniques align source and target samples in a global fashion. That is, after alignment, each source sample is expected to become simi…
A Data-driven Region Generation Framework for Spatiotemporal Transportation Service Management
Liyue Chen, Jiangyi Fang, Zhe Yu +3
MAUP (modifiable areal unit problem) is a fundamental problem for spatial data management and analysis. As an instantiation of MAUP in online transportation platforms, region gener…
Cross-center Early Sepsis Recognition by Medical Knowledge Guided Collaborative Learning for Data-scarce Hospitals
Ruiqing Ding, Fangjie Rong, Xiao Han +1
There are significant regional inequities in health resources around the world. It has become one of the most focused topics to improve health services for data-scarce hospitals an…
Vertical Federated Knowledge Transfer via Representation Distillation for Healthcare Collaboration Networks
Chung-ju Huang, Leye Wang, Xiao Han
Collaboration between healthcare institutions can significantly lessen the imbalance in medical resources across various geographic areas. However, directly sharing diagnostic info…
Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment
Jie Zhu, Leye Wang, Xiao Han
The size of deep learning models in artificial intelligence (AI) software is increasing rapidly, which hinders the large-scale deployment on resource-restricted devices (e.g., smar…
Exploring Context Generalizability in Citywide Crowd Mobility Prediction: An Analytic Framework and Benchmark
Liyue Chen, Xiaoxiang Wang, Leye Wang
Contextual features are important data sources for building citywide crowd mobility prediction models. However, the difficulty of applying context lies in the unknown generalizabil…
Cross-hospital Sepsis Early Detection via Semi-supervised Optimal Transport with Self-paced Ensemble
Ruiqing Ding, Yu Zhou, Jie Xu +7
Leveraging machine learning techniques for Sepsis early detection and diagnosis has attracted increasing interest in recent years. However, most existing methods require a large am…
Exploring the Generalizability of Spatio-Temporal Traffic Prediction: Meta-Modeling and an Analytic Framework
Leye Wang, Di Chai, Xuanzhe Liu +2
The Spatio-Temporal Traffic Prediction (STTP) problem is a classical problem with plenty of prior research efforts that benefit from traditional statistical learning and recent dee…
Secure Federated Matrix Factorization
Di Chai, Leye Wang, Kai Chen +1
To protect user privacy and meet law regulations, federated (machine) learning is obtaining vast interests in recent years. The key principle of federated learning is training a ma…
Smart City Development with Urban Transfer Learning
Leye Wang, Bin Guo, Qiang Yang
Nowadays, the smart city development levels of different cities are still unbalanced. For a large number of cities which just started development, the governments will face a criti…
Task Allocation in Mobile Crowd Sensing: State of the Art and Future Opportunities
Jiangtao Wang, Leye Wang, Yasha Wang +2
Mobile Crowd Sensing (MCS) is the special case of crowdsourcing, which leverages the smartphones with various embedded sensors and user's mobility to sense diverse phenomenon in a…