# Unsupervised Constrained Community Detection via Self-Expressive Graph Neural Network

arXiv: https://arxiv.org/abs/2011.14078 · HTML: https://mlsanity.com/paper/2011.14078/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2020.

## Built on by (most cited first, 5 of 5)

- [VGAER: Graph Neural Network Reconstruction based Community Detection](https://mlsanity.com/paper/2201.04066/) (2022)
- [Homophily-enhanced Structure Learning for Graph Clustering](https://mlsanity.com/paper/2308.05309/) (2023)
- [The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks](https://mlsanity.com/paper/2310.01144/) (2023)
- [Introduction to Graph Neural Networks for Machine Learning Engineers](https://mlsanity.com/paper/2412.19419/) (2024)
- [Clustering Node Attributed Networks with Graph Neural Networks and Self Learning](https://mlsanity.com/paper/2606.13444/) (2026)

## Abstract (arXiv)

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.