Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.08311 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911200248332288 |
|---|---|
| author | Mrini, Abdellah El Farhadkhan, Sadegh Guerraoui, Rachid |
| author_facet | Mrini, Abdellah El Farhadkhan, Sadegh Guerraoui, Rachid |
| contents | Collaborative machine learning is challenged by training-time adversarial behaviors. Existing approaches to tolerate such behaviors either rely on a central server or induce high communication costs. We propose Robust Pull-based Epidemic Learning (RPEL), a novel, scalable collaborative approach to ensure robust learning despite adversaries. RPEL does not rely on any central server and, unlike traditional methods, where communication costs grow in $\mathcal{O}(n^2)$ with the number of nodes $n$, RPEL employs a pull-based epidemic-based communication strategy that scales in $\mathcal{O}(n \log n)$. By pulling model parameters from small random subsets of nodes, RPEL significantly lowers the number of required messages without compromising convergence guarantees, which hold with high probability. Empirical results demonstrate that RPEL maintains robustness in adversarial settings, competes with all-to-all communication accuracy, and scales efficiently across large networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08311 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust and Efficient Collaborative Learning Mrini, Abdellah El Farhadkhan, Sadegh Guerraoui, Rachid Machine Learning Collaborative machine learning is challenged by training-time adversarial behaviors. Existing approaches to tolerate such behaviors either rely on a central server or induce high communication costs. We propose Robust Pull-based Epidemic Learning (RPEL), a novel, scalable collaborative approach to ensure robust learning despite adversaries. RPEL does not rely on any central server and, unlike traditional methods, where communication costs grow in $\mathcal{O}(n^2)$ with the number of nodes $n$, RPEL employs a pull-based epidemic-based communication strategy that scales in $\mathcal{O}(n \log n)$. By pulling model parameters from small random subsets of nodes, RPEL significantly lowers the number of required messages without compromising convergence guarantees, which hold with high probability. Empirical results demonstrate that RPEL maintains robustness in adversarial settings, competes with all-to-all communication accuracy, and scales efficiently across large networks. |
| title | Robust and Efficient Collaborative Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.08311 |