Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.16372 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914274998222848 |
|---|---|
| author | Shin, Hyunuk Kim, Hojin Lee, Chanyoung Lee, Yeon-Chang Kang, David Yoon Suk |
| author_facet | Shin, Hyunuk Kim, Hojin Lee, Chanyoung Lee, Yeon-Chang Kang, David Yoon Suk |
| contents | Community detection (CD) on signed networks is crucial for understanding how positive and negative relations jointly shape network structure. However, existing CD methods often yield inconsistent communities due to noisy or conflicting edge signs. In this paper, we propose ReCon, a model-agnostic post-processing framework that progressively refines community structures through four iterative steps: (1) structural refinement, (2) boundary refinement, (3) contrastive learning, and (4) clustering. Extensive experiments on eighteen synthetic and four real-world networks using four CD methods demonstrate that ReCon consistently enhances community detection accuracy, serving as an effective and easily integrable solution for reliable CD across diverse network properties. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16372 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Improving the Accuracy of Community Detection on Signed Networks via Community Refinement and Contrastive Learning Shin, Hyunuk Kim, Hojin Lee, Chanyoung Lee, Yeon-Chang Kang, David Yoon Suk Social and Information Networks Artificial Intelligence Community detection (CD) on signed networks is crucial for understanding how positive and negative relations jointly shape network structure. However, existing CD methods often yield inconsistent communities due to noisy or conflicting edge signs. In this paper, we propose ReCon, a model-agnostic post-processing framework that progressively refines community structures through four iterative steps: (1) structural refinement, (2) boundary refinement, (3) contrastive learning, and (4) clustering. Extensive experiments on eighteen synthetic and four real-world networks using four CD methods demonstrate that ReCon consistently enhances community detection accuracy, serving as an effective and easily integrable solution for reliable CD across diverse network properties. |
| title | Improving the Accuracy of Community Detection on Signed Networks via Community Refinement and Contrastive Learning |
| topic | Social and Information Networks Artificial Intelligence |
| url | https://arxiv.org/abs/2601.16372 |