LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity
LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity
Yuhan Chen, Yihong Luo, Jing Tang, Liang Yang, Siya Qiu, Chuan Wang, Xiaochun Cao
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence
Main Track. Pages 3550-3558.
https://doi.org/10.24963/ijcai.2023/395
Heterophily has been considered as an issue that hurts the performance of Graph Neural Networks (GNNs). To address this issue, some existing work uses a graph-level weighted fusion of the information of multi-hop neighbors to include more nodes with homophily. However, the heterophily might differ among nodes, which requires to consider the local topology. Motivated by it, we propose to use the local similarity (LocalSim) to learn node-level weighted fusion, which can also serve as a plug-and-play module. For better fusion, we propose a novel and efficient Initial Residual Difference Connection (IRDC) to extract more informative multi-hop information. Moreover, we provide theoretical analysis on the effectiveness of LocalSim representing node homophily on synthetic graphs. Extensive evaluations over real benchmark datasets show that our proposed method, namely Local Similarity Graph Neural Network (LSGNN), can offer comparable or superior state-of-the-art performance on both homophilic and heterophilic graphs. Meanwhile, the plug-and-play model can significantly boost the performance of existing GNNs.
Keywords:
Machine Learning: ML: Sequence and graph learning
Data Mining: DM: Mining graphs