Overlapping Community Detection with Graph Neural Networks

Oleksandr Shchur, Stephan Günnemann

Abstract: Community detection in graphs is of central importance in graph mining, machine learning and network science. Detecting overlapping communities is especially challenging, and remains an open problem. Motivated by the success of graph-based deep learning in other graph-related tasks, we study the applicability of this framework for overlapping community detection. We propose a probabilistic model for overlapping community detection based on the graph neural network architecture. Despite its simplicity, our model outperforms the existing approaches in the community recovery task by a large margin. Moreover, due to the inductive formulation, the proposed model is able to perform out-of-sample community detection for nodes that were not present at training time

Keywords: community detection, deep learning for graphs

TL;DR: Detecting overlapping communities in graphs using graph neural networks

Code: [ shchur/overlapping-community-detection](https://github.com/shchur/overlapping-community-detection)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/overlapping-community-detection-with-graph/code)