Enhancing Robustness of Federated Learning via Server Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911565389758464 |
|---|---|
| author | Mai, Van Sy Chakrabarti, Kushal La, Richard J. Maity, Dipankar |
| author_facet | Mai, Van Sy Chakrabarti, Kushal La, Richard J. Maity, Dipankar |
| contents | This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients' training data are not independent and identically distributed. We propose a heuristic algorithm that uses server learning and client update filtering in combination with geometric median aggregation. We demonstrate via experiments that this approach can achieve significant improvement in model accuracy even when the fraction of malicious clients is high, even more than $50\%$ in some cases, and the dataset utilized by the server is small and could be synthetic with its distribution not necessarily close to that of the clients' aggregated data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03226 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhancing Robustness of Federated Learning via Server Learning Mai, Van Sy Chakrabarti, Kushal La, Richard J. Maity, Dipankar Machine Learning Artificial Intelligence This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients' training data are not independent and identically distributed. We propose a heuristic algorithm that uses server learning and client update filtering in combination with geometric median aggregation. We demonstrate via experiments that this approach can achieve significant improvement in model accuracy even when the fraction of malicious clients is high, even more than $50\%$ in some cases, and the dataset utilized by the server is small and could be synthetic with its distribution not necessarily close to that of the clients' aggregated data. |
| title | Enhancing Robustness of Federated Learning via Server Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2604.03226 |