Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network

arXiv:2403.17351v1 Announce Type: new
Abstract: Under circumstances of heterophily, where nodes with different labels tend to be connected based on semantic meanings, Graph Neural Networks (GNNs) often exhibit suboptimal performance. Current studies on graph heterophily mainly focus on aggregation calibration or neighbor extension and address the heterophily issue by utilizing node features or structural information to improve GNN representations. In this paper, we propose and demonstrate that the valuable semantic information inherent in heterophily can be utilized effectively in graph …

abstract aggregation arxiv cs.lg cs.si current extension features focus gnns graph graph neural network graph neural networks information issue labels learn network networks neural network neural networks node nodes performance semantic studies type