Masked Random Noise for Communication Efficient Federated Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Shiwei, Cheng, Yingyi, Wang, Haozhao, Tang, Xing, Xu, Shijie, Luo, Weihong, Li, Yuhua, Liu, Dugang, He, Xiuqiang, Li, Ruixuan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912051166707712
author Li, Shiwei
Cheng, Yingyi
Wang, Haozhao
Tang, Xing
Xu, Shijie
Luo, Weihong
Li, Yuhua
Liu, Dugang
He, Xiuqiang
Li, Ruixuan
author_facet Li, Shiwei
Cheng, Yingyi
Wang, Haozhao
Tang, Xing
Xu, Shijie
Luo, Weihong
Li, Yuhua
Liu, Dugang
He, Xiuqiang
Li, Ruixuan
contents Federated learning is a promising distributed training paradigm that effectively safeguards data privacy. However, it may involve significant communication costs, which hinders training efficiency. In this paper, we aim to enhance communication efficiency from a new perspective. Specifically, we request the distributed clients to find optimal model updates relative to global model parameters within predefined random noise. For this purpose, we propose Federated Masked Random Noise (FedMRN), a novel framework that enables clients to learn a 1-bit mask for each model parameter and apply masked random noise (i.e., the Hadamard product of random noise and masks) to represent model updates. To make FedMRN feasible, we propose an advanced mask training strategy, called progressive stochastic masking (PSM). After local training, each client only need to transmit local masks and a random seed to the server. Additionally, we provide theoretical guarantees for the convergence of FedMRN under both strongly convex and non-convex assumptions. Extensive experiments are conducted on four popular datasets. The results show that FedMRN exhibits superior convergence speed and test accuracy compared to relevant baselines, while attaining a similar level of accuracy as FedAvg.
format Preprint
id arxiv_https___arxiv_org_abs_2408_03220
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Masked Random Noise for Communication Efficient Federated Learning
Li, Shiwei
Cheng, Yingyi
Wang, Haozhao
Tang, Xing
Xu, Shijie
Luo, Weihong
Li, Yuhua
Liu, Dugang
He, Xiuqiang
Li, Ruixuan
Machine Learning
Distributed, Parallel, and Cluster Computing
Federated learning is a promising distributed training paradigm that effectively safeguards data privacy. However, it may involve significant communication costs, which hinders training efficiency. In this paper, we aim to enhance communication efficiency from a new perspective. Specifically, we request the distributed clients to find optimal model updates relative to global model parameters within predefined random noise. For this purpose, we propose Federated Masked Random Noise (FedMRN), a novel framework that enables clients to learn a 1-bit mask for each model parameter and apply masked random noise (i.e., the Hadamard product of random noise and masks) to represent model updates. To make FedMRN feasible, we propose an advanced mask training strategy, called progressive stochastic masking (PSM). After local training, each client only need to transmit local masks and a random seed to the server. Additionally, we provide theoretical guarantees for the convergence of FedMRN under both strongly convex and non-convex assumptions. Extensive experiments are conducted on four popular datasets. The results show that FedMRN exhibits superior convergence speed and test accuracy compared to relevant baselines, while attaining a similar level of accuracy as FedAvg.
title Masked Random Noise for Communication Efficient Federated Learning
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2408.03220