2025/05/09 by Abdelfateh Bekkair, Bekkair, Abdelfateh, Slimane Bellaouar +3
Biochemistry, Genetics and Molecular Biology · Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Bioinformatics and Genomic Networks #Complex Network Analysis Techniques #FOS: Computer and information sciences #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.2505.05965
openalex publication_date 2025/05/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Community detection in networks with overlapping structures remains a significant challenge, particularly in noisy real-world environments where integrating topology, node attributes, and prior information is critical. To address this, we propose a semi-supervised graph autoencoder that combines graph multi-head attention and modularity maximization to robustly detect overlapping communities. The model learns semantic representations by fusing structural, attribute, and prior knowledge while explicitly addressing noise in node features. Key innovations include a noise-resistant architecture and a semantic semi-supervised design optimized for community quality through modularity constraints. Experiments demonstrate superior performance the model outperforms state-of-the-art methods in overlapping community detection (improvements in NMI and F1-score) and exhibits exceptional robustness to attribute noise, maintaining stable performance under 60% feature corruption. These results highlight the importance of integrating attribute semantics and structural patterns for accurate community discovery in complex networks.