UCoDe: Unified Community Detection with Graph Convolutional Networks

TL;DR

UCoDe is a novel graph neural network approach that simultaneously detects overlapping and non-overlapping communities in attributed graphs using a contrastive loss, outperforming existing methods across diverse datasets.

Contribution

The paper introduces UCoDe, the first unified community detection method capable of identifying both overlapping and non-overlapping communities with minimal hyper-parameter tuning.

Findings

UCoDe achieves top or near-top performance on real datasets.

It effectively captures community structures regardless of data distribution.

The method simplifies community detection by unifying overlapping and non-overlapping detection.

Abstract

Community detection finds homogeneous groups of nodes in a graph. Existing approaches either partition the graph into disjoint, non-overlapping, communities, or determine only overlapping communities. To date, no method supports both detections of overlapping and non-overlapping communities. We propose UCoDe, a unified method for community detection in attributed graphs that detects both overlapping and non-overlapping communities by means of a novel contrastive loss that captures node similarity on a macro-scale. Our thorough experimental assessment on real data shows that, regardless of the data distribution, our method is either the top performer or among the top performers in both overlapping and non-overlapping detection without burdensome hyper-parameter tuning.