Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.17381 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908913072340992 |
|---|---|
| author | Bekdache, Omar Shanbhag, Naresh |
| author_facet | Bekdache, Omar Shanbhag, Naresh |
| contents | Federated learning (FL) emerged as a popular distributed algorithm to train machine learning models on edge devices while preserving data privacy. However, FL systems face challenges due to client-side computational constraints and from a lack of robustness to naturally occurring common corruptions such as noise, blur, and weather effects. Existing robust training methods are computationally expensive and unsuitable for resource-constrained clients. We propose a novel data-agnostic robust training (DART) plug-in that can be deployed in any FL system to enhance robustness at zero client overhead. DART operates at the server-side and does not require private data access, ensuring seamless integration in existing FL systems. Extensive experiments showcase DART's ability to enhance robustness of state-of-the-art FL systems, establishing it as a practical and scalable solution for real-world robust FL deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17381 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DART: A Server-side Plug-in for Resource-efficient Robust Federated Learning Bekdache, Omar Shanbhag, Naresh Machine Learning Federated learning (FL) emerged as a popular distributed algorithm to train machine learning models on edge devices while preserving data privacy. However, FL systems face challenges due to client-side computational constraints and from a lack of robustness to naturally occurring common corruptions such as noise, blur, and weather effects. Existing robust training methods are computationally expensive and unsuitable for resource-constrained clients. We propose a novel data-agnostic robust training (DART) plug-in that can be deployed in any FL system to enhance robustness at zero client overhead. DART operates at the server-side and does not require private data access, ensuring seamless integration in existing FL systems. Extensive experiments showcase DART's ability to enhance robustness of state-of-the-art FL systems, establishing it as a practical and scalable solution for real-world robust FL deployment. |
| title | DART: A Server-side Plug-in for Resource-efficient Robust Federated Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.17381 |