META-CODE: Community Detection via Exploratory Learning in Topologically Unknown Networks
This addresses a fundamental problem in network analysis for social networks where topology is unknown, offering a novel method to reduce costly data acquisition, though it appears incremental as it builds on existing techniques like GNNs.
The paper tackled the problem of detecting overlapping communities in networks with unknown topology due to privacy or access restrictions, by proposing META-CODE, an end-to-end solution using exploratory learning with node metadata, which demonstrated superiority over benchmark methods, effectiveness of the training model, and fast network exploration.
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.