A Noise-Resilient Semi-Supervised Graph Autoencoder for Overlapping Semantic Community Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913828542873600 |
|---|---|
| author | Bekkair, Abdelfateh Bellaouar, Slimane Oulad-Naoui, Slimane |
| author_facet | Bekkair, Abdelfateh Bellaouar, Slimane Oulad-Naoui, Slimane |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_05965 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Noise-Resilient Semi-Supervised Graph Autoencoder for Overlapping Semantic Community Detection Bekkair, Abdelfateh Bellaouar, Slimane Oulad-Naoui, Slimane Social and Information Networks Artificial Intelligence 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. |
| title | A Noise-Resilient Semi-Supervised Graph Autoencoder for Overlapping Semantic Community Detection |
| topic | Social and Information Networks Artificial Intelligence |
| url | https://arxiv.org/abs/2505.05965 |