English

FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning

Machine Learning 2023-01-20 v3 Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@article{arxiv.2108.06098,
  title  = {FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning},
  author = {Nam Hyeon-Woo and Moon Ye-Bin and Tae-Hyun Oh},
  journal= {arXiv preprint arXiv:2108.06098},
  year   = {2023}
}

Comments

Accepted at ICLR 2022