56 citations · 58 across the 5 of their papers we have counts for
5 papers
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…
Heterophilous Distribution Propagation for Graph Neural Networks
Zhuonan Zheng, Sheng Zhou, Hongjia Xu +6
Graph Neural Networks (GNNs) have achieved remarkable success in various graph mining tasks by aggregating information from neighborhoods for representation learning. The success r…
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…
A Survey on Graph Condensation
Hongjia Xu, Liangliang Zhang, Yao Ma +3
Analytics on large-scale graphs have posed significant challenges to computational efficiency and resource requirements. Recently, Graph condensation (GC) has emerged as a solution…
A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions
Sheng Zhou, Hongjia Xu, Zhuonan Zheng +7
Clustering is a fundamental machine learning task which has been widely studied in the literature. Classic clustering methods follow the assumption that data are represented as fea…