WOCD: A Semi-Supervised Method for Overlapping Community Detection Using Weak Cliques

2025-07-30

AI Summary

Existing GNN-based overlapping community detection methods struggle to effectively integrate link, attribute, and prior knowledge, while suffering from limited receptive fields and oversmoothing. To address these challenges, this paper proposes a weak-clique-driven semi-supervised framework: first, high-quality pseudo-labels are generated leveraging weak-clique structures to inject prior knowledge; second, a single-layer hybrid architecture—combining Graph Transformer and GNN—is designed to preserve local structural awareness, mitigate oversmoothing, and jointly model topological and attribute information. The method unifies these three heterogeneous information sources, significantly enhancing model generalizability and discriminative power. Extensive experiments on eight real-world attributed graph datasets demonstrate that our approach consistently outperforms state-of-the-art semi-supervised overlapping community detection methods in accuracy.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Semi-Supervised Learning
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Overlapping community detection (OCD) is a fundamental graph data analysis task for extracting graph patterns. Traditional OCD methods can be broadly divided into node clustering and link clustering approaches, both of which rely solely on link information to identify overlapping communities. In recent years, deep learning-based methods have made significant advancements for this task. However, existing GNN-based approaches often face difficulties in effectively integrating link, attribute, and prior information, along with challenges like limited receptive fields and over-smoothing, which hinder their performance on complex overlapping community detection. In this paper, we propose a Weak-clique based Overlapping Community Detection method, namely WOCD, which incorporates prior information and optimizes the use of link information to improve detection accuracy. Specifically, we introduce pseudo-labels within a semi-supervised framework to strengthen the generalization ability, making WOCD more versatile. Furthermore, we initialize pseudo-labels using weak cliques to fully leverage link and prior information, leading to better detection accuracy. Additionally, we employ a single-layer Graph Transformer combined with GNN, which achieves significant performance improvements while maintaining efficiency. We evaluate WOCD on eight real-world attributed datasets, and the results demonstrate that it outperforms the state-of-the-art semi-supervised OCD method by a significant margin in terms of accuracy.

Problem

• Detects overlapping communities using weak cliques
• Integrates link, attribute, and prior information effectively
• Improves accuracy with semi-supervised pseudo-labels

Innovation

• Uses weak cliques for community detection
• Integrates pseudo-labels in semi-supervised framework
• Combines Graph Transformer with GNN