In this work, we propose a communication-efficient parameterization, FedPara, for federated learning (FL) to overcome the burdens on frequent model uploads and downloads. Our method re-parameterizes weight parameters of layers using low-rank weights followed by the Hadamard product. Compared to the conventional low-rank parameterization, our FedPara method is not restricted to low-rank constraints, and thereby it has a far larger capacity. This property enables to achieve comparable performance while requiring 3 to 10 times lower communication costs than the model with the original layers, which is not achievable by the traditional low-rank methods. The efficiency of our method can be further improved by combining with other efficient FL optimizers. In addition, we extend our method to a personalized FL application, pFedPara, which separates parameters into global and local ones. We show that pFedPara outperforms competing personalized FL methods with more than three times fewer parameters.
FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning
FedPara is a communication-efficient parameterization for federated learning that uses low-rank weights and Hadamard products, achieving lower communication costs compared to traditional methods, and pFedPara extends it for personalized FL with better performance.
- Year
- 2021
- Venue
- fedpara-low-rank-hadamard-product-for
- Authors
- 3
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2108.06098v3ARXIV-DEFAULT
- TL;DR
- Semantic Scholar