← Search

Zhuonan Zheng

2 accepted papers

2025

Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective

NeurIPS 2025poster

Graph Neural Networks (GNNs) have achieved great success but are often considered to be challenged by varying levels of homophily in graphs. Recent empirical studies have surprisingly shown that homophilic GNNs can perform well across datasets of different homophily levels with proper hyperparameter…

Cited by 0SourcecodeScholar
2025

Understanding and Enhancing Message Passing on Heterophilic Graphs via Compatibility Matrix

NeurIPS 2025poster

Graph Neural Networks (GNNs) excel in graph mining tasks thanks to their message-passing mechanism, which aligns with the homophily assumption. However, connected nodes can also exhibit inconsistent behaviors, termed heterophilic patterns, sparking interest in heterophilic GNNs (HTGNNs). Although th…

Cited by 0SourceScholar