Multi-view Contrastive Graph Clustering

Erlin Pan, zhao kang

Keywords: multi-view clustering, contrastive learning, graph learning, subspace clustering

TL;DR: This paper develops a clustering method for multi-view attributed graph data. It applied graph filtering to obtain a good representation and contrastive regularizer to achieve a high quality graph.

Abstract: With the explosive growth of information technology, multi-view graph data have become increasingly prevalent and valuable. Most existing multi-view clustering techniques either focus on the scenario of multiple graphs or multi-view attributes. In this paper, we propose a generic framework to cluster multi-view attributed graph data. Specifically, inspired by the success of contrastive learning, we propose multi-view contrastive graph clustering (MCGC) method to learn a consensus graph since the original graph could be noisy or incomplete and is not directly applicable. Our method composes of two key steps: we first filter out the undesirable high-frequency noise while preserving the graph geometric features via graph filtering and obtain a smooth representation of nodes; we then learn a consensus graph regularized by graph contrastive loss. Results on several benchmark datasets show the superiority of our method with respect to state-of-the-art approaches. In particular, our simple approach outperforms existing deep learning-based methods.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/Panern/MCGC

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2110.11842/code)