activity
20142025
most citedCollaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation

15 citations · 63 across the 16 of their papers we have counts for

collaborators

11 papers

cs.DC20242 cited

OFL-W3: A One-shot Federated Learning System on Web 3.0

Linshan Jiang, Moming Duan, Bingsheng He +4

Federated Learning (FL) addresses the challenges posed by data silos, which arise from privacy, security regulations, and ownership concerns. Despite these barriers, FL enables the…

cs.DC2024

FlowWalker: A Memory-efficient and High-performance GPU-based Dynamic Graph Random Walk Framework

Junyi Mei, Shixuan Sun, Chao Li +9

Dynamic graph random walk (DGRW) emerges as a practical tool for capturing structural relations within a graph. Effectively executing DGRW on GPU presents certain challenges. First…

cs.LG202415 cited

Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation

Zhen Zhang, Meihan Liu, Anhui Wang +4

Unsupervised Graph Domain Adaptation (UGDA) has emerged as a practical solution to transfer knowledge from a label-rich source graph to a completely unlabelled target graph. Howeve…

cs.LG20242 cited

BuffGraph: Enhancing Class-Imbalanced Node Classification via Buffer Nodes

Qian Wang, Zemin Liu, Zhen Zhang +1

Class imbalance in graph-structured data, where minor classes are significantly underrepresented, poses a critical challenge for Graph Neural Networks (GNNs). To address this chall…

cs.AI20235 cited

Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFT

Zhen Zhang, Bingqiao Luo, Shengliang Lu +1

Numerous studies have been conducted to investigate the properties of large-scale temporal graphs. Despite the ubiquity of these graphs in real-world scenarios, it's usually imprac…

cs.DC202310 cited

FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs

Zhenheng Tang, Yuxin Wang, Xin He +8

The rapid growth of memory and computation requirements of large language models (LLMs) has outpaced the development of hardware, hindering people who lack large-scale high-end GPU…