RANA: Robust Active Learning for Noisy Network Alignment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912526838530048 |
|---|---|
| author | Nan, Yixuan Lin, Xixun Shang, Yanmin Li, Zhuofan Zhao, Can Cao, Yanan |
| author_facet | Nan, Yixuan Lin, Xixun Shang, Yanmin Li, Zhuofan Zhao, Can Cao, Yanan |
| contents | Network alignment has attracted widespread attention in various fields. However, most existing works mainly focus on the problem of label sparsity, while overlooking the issue of noise in network alignment, which can substantially undermine model performance. Such noise mainly includes structural noise from noisy edges and labeling noise caused by human-induced and process-driven errors. To address these problems, we propose RANA, a Robust Active learning framework for noisy Network Alignment. RANA effectively tackles both structure noise and label noise while addressing the sparsity of anchor link annotations, which can improve the robustness of network alignment models. Specifically, RANA introduces the proposed Noise-aware Selection Module and the Label Denoising Module to address structural noise and labeling noise, respectively. In the first module, we design a noise-aware maximization objective to select node pairs, incorporating a cleanliness score to address structural noise. In the second module, we propose a novel multi-source fusion denoising strategy that leverages model and twin node pairs labeling to provide more accurate labels for node pairs. Empirical results on three real-world datasets demonstrate that RANA outperforms state-of-the-art active learning-based methods in alignment accuracy. Our code is available at https://github.com/YXNan0110/RANA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22434 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RANA: Robust Active Learning for Noisy Network Alignment Nan, Yixuan Lin, Xixun Shang, Yanmin Li, Zhuofan Zhao, Can Cao, Yanan Machine Learning Network alignment has attracted widespread attention in various fields. However, most existing works mainly focus on the problem of label sparsity, while overlooking the issue of noise in network alignment, which can substantially undermine model performance. Such noise mainly includes structural noise from noisy edges and labeling noise caused by human-induced and process-driven errors. To address these problems, we propose RANA, a Robust Active learning framework for noisy Network Alignment. RANA effectively tackles both structure noise and label noise while addressing the sparsity of anchor link annotations, which can improve the robustness of network alignment models. Specifically, RANA introduces the proposed Noise-aware Selection Module and the Label Denoising Module to address structural noise and labeling noise, respectively. In the first module, we design a noise-aware maximization objective to select node pairs, incorporating a cleanliness score to address structural noise. In the second module, we propose a novel multi-source fusion denoising strategy that leverages model and twin node pairs labeling to provide more accurate labels for node pairs. Empirical results on three real-world datasets demonstrate that RANA outperforms state-of-the-art active learning-based methods in alignment accuracy. Our code is available at https://github.com/YXNan0110/RANA. |
| title | RANA: Robust Active Learning for Noisy Network Alignment |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.22434 |