Unsupervised Constrained Community Detection via Self-Expressive Graph Neural Network

TL;DR

This paper introduces an unsupervised, end-to-end graph neural network that leverages self-expressiveness for community detection, outperforming existing methods on standard datasets.

Contribution

It pioneers the integration of self-expressiveness with self-supervised GNNs for direct, unsupervised community detection in graphs.

Findings

Achieves state-of-the-art community detection results

Operates in an end-to-end unsupervised manner

Outperforms traditional decoupled methods

Abstract

Graph neural networks (GNNs) are able to achieve promising performance on multiple graph downstream tasks such as node classification and link prediction. Comparatively lesser work has been done to design GNNs which can operate directly for community detection on graphs. Traditionally, GNNs are trained on a semi-supervised or self-supervised loss function and then clustering algorithms are applied to detect communities. However, such decoupled approaches are inherently sub-optimal. Designing an unsupervised loss function to train a GNN and extract communities in an integrated manner is a fundamental challenge. To tackle this problem, we combine the principle of self-expressiveness with the framework of self-supervised graph neural network for unsupervised community detection for the first time in literature. Our solution is trained in an end-to-end fashion and achieves state-of-the-art community detection performance on multiple publicly available datasets.