5 papers
Clarify Confused Nodes via Separated Learning
Jiajun Zhou, Shengbo Gong, Xuanze Chen +4
Graph neural networks (GNNs) have achieved remarkable advances in graph-oriented tasks. However, real-world graphs invariably contain a certain proportion of heterophilous nodes, c…
Enhancing Ethereum Fraud Detection via Generative and Contrastive Self-supervision
Chenxiang Jin, Jiajun Zhou, Chenxuan Xie +3
The rampant fraudulent activities on Ethereum hinder the healthy development of the blockchain ecosystem, necessitating the reinforcement of regulations. However, multiple imbalanc…
Rethinking Graph Transformer Architecture Design for Node Classification
Jiajun Zhou, Xuanze Chen, Chenxuan Xie +3
Graph Transformer (GT), as a special type of Graph Neural Networks (GNNs), utilizes multi-head attention to facilitate high-order message passing. However, this also imposes severa…
PathMLP: Smooth Path Towards High-order Homophily
Jiajun Zhou, Chenxuan Xie, Shengbo Gong +4
Real-world graphs exhibit increasing heterophily, where nodes no longer tend to be connected to nodes with the same label, challenging the homophily assumption of classical graph n…
Data Augmentation on Graphs: A Technical Survey
Jiajun Zhou, Chenxuan Xie, Shengbo Gong +4
In recent years, graph representation learning has achieved remarkable success while suffering from low-quality data problems. As a mature technology to improve data quality in com…