Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Provable Filter for Real-world Graph Clustering

About

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 solution with theoretical support. Interestingly, we find that most homophilic and heterophilic edges can be correctly identified on the basis of neighbor information. Motivated by this finding, we construct two graphs that are highly homophilic and heterophilic, respectively. They are used to build low-pass and high-pass filters to capture holistic information. Important features are further enhanced by the squeeze-and-excitation block. We validate our approach through extensive experiments on both homophilic and heterophilic graphs. Empirical results demonstrate the superiority of our method compared to state-of-the-art clustering methods.

Xuanting Xie, Erlin Pan, Zhao Kang, Wenyu Chen, Bingheng Li• 2024

Related benchmarks

TaskDatasetResultRank
Node ClusteringCora
Accuracy76.51
133
Node ClusteringCiteseer
NMI45.45
130
Graph ClusteringAMAP
Accuracy78.5
35
Graph ClusteringPubmed
Accuracy72.89
31
Co-Salient Object DetectioniCoseg
S-measure (S_alpha)83.2
24
Graph ClusteringChameleon
Accuracy41.28
14
Graph ClusteringCornell
Accuracy66.12
13
Graph ClusteringWisconsin
Accuracy74.1
13
Graph ClusteringUAT
Accuracy56.81
12
Graph ClusteringWashington
Accuracy70.43
12
Showing 10 of 13 rows

Other info

Follow for update