Neighborhood and Global Perturbations Supported SAM in Federated Learning: From Local Tweaks To Global Awareness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Boyuan, Peng, Zihao, Li, Yafei, Xu, Mingliang, Chen, Shengbo, Ji, Baofeng, Shen, Cong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929478491439104
author Li, Boyuan
Peng, Zihao
Li, Yafei
Xu, Mingliang
Chen, Shengbo
Ji, Baofeng
Shen, Cong
author_facet Li, Boyuan
Peng, Zihao
Li, Yafei
Xu, Mingliang
Chen, Shengbo
Ji, Baofeng
Shen, Cong
contents Federated Learning (FL) can be coordinated under the orchestration of a central server to collaboratively build a privacy-preserving model without the need for data exchange. However, participant data heterogeneity leads to local optima divergence, subsequently affecting convergence outcomes. Recent research has focused on global sharpness-aware minimization (SAM) and dynamic regularization techniques to enhance consistency between global and local generalization and optimization objectives. Nonetheless, the estimation of global SAM introduces additional computational and memory overhead, while dynamic regularization suffers from bias in the local and global dual variables due to training isolation. In this paper, we propose a novel FL algorithm, FedTOGA, designed to consider optimization and generalization objectives while maintaining minimal uplink communication overhead. By linking local perturbations to global updates, global generalization consistency is improved. Additionally, global updates are used to correct local dynamic regularizers, reducing dual variables bias and enhancing optimization consistency. Global updates are passively received by clients, reducing overhead. We also propose neighborhood perturbation to approximate local perturbation, analyzing its strengths and limitations. Theoretical analysis shows FedTOGA achieves faster convergence $O(1/T)$ under non-convex functions. Empirical studies demonstrate that FedTOGA outperforms state-of-the-art algorithms, with a 1\% accuracy increase and 30\% faster convergence, achieving state-of-the-art.
format Preprint
id arxiv_https___arxiv_org_abs_2408_14144
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Neighborhood and Global Perturbations Supported SAM in Federated Learning: From Local Tweaks To Global Awareness
Li, Boyuan
Peng, Zihao
Li, Yafei
Xu, Mingliang
Chen, Shengbo
Ji, Baofeng
Shen, Cong
Machine Learning
Distributed, Parallel, and Cluster Computing
Federated Learning (FL) can be coordinated under the orchestration of a central server to collaboratively build a privacy-preserving model without the need for data exchange. However, participant data heterogeneity leads to local optima divergence, subsequently affecting convergence outcomes. Recent research has focused on global sharpness-aware minimization (SAM) and dynamic regularization techniques to enhance consistency between global and local generalization and optimization objectives. Nonetheless, the estimation of global SAM introduces additional computational and memory overhead, while dynamic regularization suffers from bias in the local and global dual variables due to training isolation. In this paper, we propose a novel FL algorithm, FedTOGA, designed to consider optimization and generalization objectives while maintaining minimal uplink communication overhead. By linking local perturbations to global updates, global generalization consistency is improved. Additionally, global updates are used to correct local dynamic regularizers, reducing dual variables bias and enhancing optimization consistency. Global updates are passively received by clients, reducing overhead. We also propose neighborhood perturbation to approximate local perturbation, analyzing its strengths and limitations. Theoretical analysis shows FedTOGA achieves faster convergence $O(1/T)$ under non-convex functions. Empirical studies demonstrate that FedTOGA outperforms state-of-the-art algorithms, with a 1\% accuracy increase and 30\% faster convergence, achieving state-of-the-art.
title Neighborhood and Global Perturbations Supported SAM in Federated Learning: From Local Tweaks To Global Awareness
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2408.14144