Restructuring Graph for Higher Homophily via Adaptive Spectral Clustering

arXiv:2206.02386v3 Announce Type: replace
Abstract: While a growing body of literature has been studying new Graph Neural Networks (GNNs) that work on both homophilic and heterophilic graphs, little has been done on adapting classical GNNs to less-homophilic graphs. Although the ability to handle less-homophilic graphs is restricted, classical GNNs still stand out in several nice properties such as efficiency, simplicity, and explainability. In this work, we propose a novel graph restructuring method that can be integrated into any type of …

abstract arxiv clustering cs.lg cs.si gnns graph graph neural networks graphs literature networks neural networks restructuring studying type via while work