META-CODE: Community Detection via Exploratory Learning in Topologically Unknown Networks

TL;DR

META-CODE is a novel method for detecting overlapping communities in networks with unknown topology, leveraging exploratory learning and node metadata to overcome data access restrictions.

Contribution

It introduces an end-to-end approach combining network inference, GNN-based embedding, and iterative exploration for community detection without full network data.

Findings

Outperforms benchmark methods in overlapping community detection

Effective GNN training with a new reconstruction loss

Enables fast network exploration with limited data

Abstract

The discovery of community structures in social networks has gained considerable attention as a fundamental problem for various network analysis tasks. However, due to privacy concerns or access restrictions, the network structure is often unknown, thereby rendering established community detection approaches ineffective without costly data acquisition. To tackle this challenge, we present META-CODE, a novel end-to-end solution for detecting overlapping communities in networks with unknown topology via exploratory learning aided by easy-to-collect node metadata. Specifically, META-CODE consists of three steps: 1) initial network inference, 2) node-level community-affiliation embedding based on graph neural networks (GNNs) trained by our new reconstruction loss, and 3) network exploration via community-affiliation-based node queries, where Steps 2 and 3 are performed iteratively. Experimental results demonstrate that META-CODE exhibits (a) superiority over benchmark methods for overlapping community detection, (b) the effectiveness of our training model, and (c) fast network exploration.