Provable Filter for Real-world Graph Clustering

arXiv:2403.03666v1 Announce Type: new
Abstract: Graph clustering, an important unsupervised problem, has been shown to be more resistant to advances in Graph Neural Networks (GNNs). In addition, almost all clustering methods focus on homophilic graphs and ignore heterophily. This significantly limits their applicability in practice, since real-world graphs exhibit a structural disparity and cannot simply be classified as homophily and heterophily. Thus, a principled way to handle practical graphs is urgently needed. To fill this gap, we provide a novel …

abstract advances arxiv clustering cs.lg filter focus gnns graph graph neural networks graphs networks neural networks practice type unsupervised world