4 papers · 1 filter
Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness-Generalization Perspective
Ming Gu, Zhuonan Zheng, Sheng Zhou +5
Graph Neural Networks (GNNs) have achieved great success but are often considered to be challenged by varying levels of homophily in graphs. Recent \textit{empirical} studies have…
OpenGT: A Comprehensive Benchmark For Graph Transformers
Jiachen Tang, Zhonghao Wang, Sirui Chen +3
Graph Transformers (GTs) have recently demonstrated remarkable performance across diverse domains. By leveraging attention mechanisms, GTs are capable of modeling long-range depend…
Towards a Unified Framework of Clustering-based Anomaly Detection
Zeyu Fang, Ming Gu, Sheng Zhou +4
Unsupervised Anomaly Detection (UAD) plays a crucial role in identifying abnormal patterns within data without labeled examples, holding significant practical implications across v…
Revisiting the Message Passing in Heterophilous Graph Neural Networks
Zhuonan Zheng, Yuanchen Bei, Sheng Zhou +6
Graph Neural Networks (GNNs) have demonstrated strong performance in graph mining tasks due to their message-passing mechanism, which is aligned with the homophily assumption that…