Unsupervised constrained community detection via self-expressive graph neural network

Sambaran Bandyopadhyay, Vishal Peter
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, PMLR 161:1078-1088, 2021.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v161-bandyopadhyay21a, title = {Unsupervised constrained community detection via self-expressive graph neural network}, author = {Bandyopadhyay, Sambaran and Peter, Vishal}, booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence}, pages = {1078--1088}, year = {2021}, editor = {de Campos, Cassio and Maathuis, Marloes H.}, volume = {161}, series = {Proceedings of Machine Learning Research}, month = {27--30 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v161/bandyopadhyay21a/bandyopadhyay21a.pdf}, url = {https://proceedings.mlr.press/v161/bandyopadhyay21a.html}, 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.} }
Endnote
%0 Conference Paper %T Unsupervised constrained community detection via self-expressive graph neural network %A Sambaran Bandyopadhyay %A Vishal Peter %B Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2021 %E Cassio de Campos %E Marloes H. Maathuis %F pmlr-v161-bandyopadhyay21a %I PMLR %P 1078--1088 %U https://proceedings.mlr.press/v161/bandyopadhyay21a.html %V 161 %X 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.
APA
Bandyopadhyay, S. & Peter, V.. (2021). Unsupervised constrained community detection via self-expressive graph neural network. Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 161:1078-1088 Available from https://proceedings.mlr.press/v161/bandyopadhyay21a.html.

Related Material