FedNC: A Secure and Efficient Federated Learning Method with Network Coding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910290405228544 |
|---|---|
| author | Shi, Yuchen Zhu, Zheqi Fan, Pingyi Letaief, Khaled B. Peng, Chenghui |
| author_facet | Shi, Yuchen Zhu, Zheqi Fan, Pingyi Letaief, Khaled B. Peng, Chenghui |
| contents | Federated Learning (FL) is a promising distributed learning mechanism which still faces two major challenges, namely privacy breaches and system efficiency. In this work, we reconceptualize the FL system from the perspective of network information theory, and formulate an original FL communication framework, FedNC, which is inspired by Network Coding (NC). The main idea of FedNC is mixing the information of the local models by making random linear combinations of the original parameters, before uploading for further aggregation. Due to the benefits of the coding scheme, both theoretical and experimental analysis indicate that FedNC improves the performance of traditional FL in several important ways, including security, efficiency, and robustness. To the best of our knowledge, this is the first framework where NC is introduced in FL. As FL continues to evolve within practical network frameworks, more variants can be further designed based on FedNC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_03292 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | FedNC: A Secure and Efficient Federated Learning Method with Network Coding Shi, Yuchen Zhu, Zheqi Fan, Pingyi Letaief, Khaled B. Peng, Chenghui Machine Learning Cryptography and Security Information Theory Federated Learning (FL) is a promising distributed learning mechanism which still faces two major challenges, namely privacy breaches and system efficiency. In this work, we reconceptualize the FL system from the perspective of network information theory, and formulate an original FL communication framework, FedNC, which is inspired by Network Coding (NC). The main idea of FedNC is mixing the information of the local models by making random linear combinations of the original parameters, before uploading for further aggregation. Due to the benefits of the coding scheme, both theoretical and experimental analysis indicate that FedNC improves the performance of traditional FL in several important ways, including security, efficiency, and robustness. To the best of our knowledge, this is the first framework where NC is introduced in FL. As FL continues to evolve within practical network frameworks, more variants can be further designed based on FedNC. |
| title | FedNC: A Secure and Efficient Federated Learning Method with Network Coding |
| topic | Machine Learning Cryptography and Security Information Theory |
| url | https://arxiv.org/abs/2305.03292 |