Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2210.08106 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913708517621760 |
|---|---|
| author | Overman, Tom Blum, Garrett Klabjan, Diego |
| author_facet | Overman, Tom Blum, Garrett Klabjan, Diego |
| contents | Very few methods for hybrid federated learning, where clients only hold subsets of both features and samples, exist. Yet, this scenario is extremely important in practical settings. We provide a fast, robust algorithm for hybrid federated learning that hinges on Fenchel Duality. We prove the convergence of the algorithm to the same solution as if the model is trained centrally in a variety of practical regimes. Furthermore, we provide experimental results that demonstrate the performance improvements of the algorithm over a commonly used method in federated learning, FedAvg, and an existing hybrid FL algorithm, HyFEM. We also provide privacy considerations and necessary steps to protect client data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_08106 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | A Primal-Dual Algorithm for Hybrid Federated Learning Overman, Tom Blum, Garrett Klabjan, Diego Machine Learning Very few methods for hybrid federated learning, where clients only hold subsets of both features and samples, exist. Yet, this scenario is extremely important in practical settings. We provide a fast, robust algorithm for hybrid federated learning that hinges on Fenchel Duality. We prove the convergence of the algorithm to the same solution as if the model is trained centrally in a variety of practical regimes. Furthermore, we provide experimental results that demonstrate the performance improvements of the algorithm over a commonly used method in federated learning, FedAvg, and an existing hybrid FL algorithm, HyFEM. We also provide privacy considerations and necessary steps to protect client data. |
| title | A Primal-Dual Algorithm for Hybrid Federated Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2210.08106 |