Unsupervised constrained community detection via self-expressive graph neural network

Bandyopadhyay, S and Peter, V (2021) Unsupervised constrained community detection via self-expressive graph neural network. In: 37th Conference on Uncertainty in Artificial Intelligence, UAI 2021, 1088, pp. 1078-1088.

PDF uai_2021.pdf - Published Version Restricted to Registered users only Download (617kB) | Request a copy

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.

Item Type:	Conference Paper
Publication:	Proceedings of Machine Learning Research
Publisher:	ML Research Press
Additional Information:	The copyright for this article belongs to Association For Uncertainty in Artificial Intelligence (AUAI).
Keywords:	Clustering algorithms; Machine learning; Population dynamics, Classification prediction; Community detection; Design graphs; Down-stream; End to end; Graph neural networks; Link prediction; Loss functions; Performance; Semi-supervised, Graph neural networks
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	25 Jul 2023 10:41
Last Modified:	25 Jul 2023 10:41
URI:	https://eprints.iisc.ac.in/id/eprint/82661

Actions (login required)

View Item