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. Our code is provided at https://github.com/draym28/LSGNN.

翻译：异质性（Heterophily）被认为会损害图神经网络（GNN）的性能。针对该问题，现有工作通常采用图级别的多跳邻居信息加权融合策略，以引入更多同质性节点。然而，异质性在不同节点间可能存在差异，这要求考虑局部拓扑结构。受此启发，我们提出利用局部相似性（LocalSim）学习节点级别的加权融合方法，该方法可作为即插即用模块。为优化融合效果，我们设计了一种新型高效的初始残差差分连接（IRDC）机制，以提取更具信息量的多跳邻域特征。此外，我们在合成图上对LocalSim表征节点同质性的有效性进行了理论分析。在真实基准数据集上的大量实验表明，所提出的局部相似性图神经网络（LSGNN）在同质性与异质性图上均能达到可比或更优的最新性能。同时，该即插即用模型能显著提升现有GNN的性能。我们的代码已开源至 https://github.com/draym28/LSGNN。