Advancing Community Detection with Graph Convolutional Neural Networks: Bridging Topological and Attributive Cohesion
This work addresses community detection for social network analysis, offering an incremental improvement by refining existing methods to better balance topological and attributive cohesion.
The paper tackled the problem of suboptimal community detection in social networks by proposing TAS-Com, a method that uses a novel loss function and the Leiden algorithm to achieve better trade-offs between modularity and compliance with human labels, resulting in significant outperformance over state-of-the-art algorithms on benchmark networks.
Community detection, a vital technology for real-world applications, uncovers cohesive node groups (communities) by leveraging both topological and attribute similarities in social networks. However, existing Graph Convolutional Networks (GCNs) trained to maximize modularity often converge to suboptimal solutions. Additionally, directly using human-labeled communities for training can undermine topological cohesiveness by grouping disconnected nodes based solely on node attributes. We address these issues by proposing a novel Topological and Attributive Similarity-based Community detection (TAS-Com) method. TAS-Com introduces a novel loss function that exploits the highly effective and scalable Leiden algorithm to detect community structures with global optimal modularity. Leiden is further utilized to refine human-labeled communities to ensure connectivity within each community, enabling TAS-Com to detect community structures with desirable trade-offs between modularity and compliance with human labels. Experimental results on multiple benchmark networks confirm that TAS-Com can significantly outperform several state-of-the-art algorithms.