Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2308.12581 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914726923993088 |
|---|---|
| author | Zhao, Puning Yu, Fei Wan, Zhiguo |
| author_facet | Zhao, Puning Yu, Fei Wan, Zhiguo |
| contents | Federated learning systems are susceptible to adversarial attacks. To combat this, we introduce a novel aggregator based on Huber loss minimization, and provide a comprehensive theoretical analysis. Under independent and identically distributed (i.i.d) assumption, our approach has several advantages compared to existing methods. Firstly, it has optimal dependence on $ε$, which stands for the ratio of attacked clients. Secondly, our approach does not need precise knowledge of $ε$. Thirdly, it allows different clients to have unequal data sizes. We then broaden our analysis to include non-i.i.d data, such that clients have slightly different distributions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_12581 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Huber Loss Minimization Approach to Byzantine Robust Federated Learning Zhao, Puning Yu, Fei Wan, Zhiguo Machine Learning Artificial Intelligence Federated learning systems are susceptible to adversarial attacks. To combat this, we introduce a novel aggregator based on Huber loss minimization, and provide a comprehensive theoretical analysis. Under independent and identically distributed (i.i.d) assumption, our approach has several advantages compared to existing methods. Firstly, it has optimal dependence on $ε$, which stands for the ratio of attacked clients. Secondly, our approach does not need precise knowledge of $ε$. Thirdly, it allows different clients to have unequal data sizes. We then broaden our analysis to include non-i.i.d data, such that clients have slightly different distributions. |
| title | A Huber Loss Minimization Approach to Byzantine Robust Federated Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2308.12581 |