FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Zhiqin, Zhang, Yonggang, Li, Chenxin, Cheung, Yiu-ming, Han, Bo, Yuan, Yixuan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912665832521728
author Yang, Zhiqin
Zhang, Yonggang
Li, Chenxin
Cheung, Yiu-ming
Han, Bo
Yuan, Yixuan
author_facet Yang, Zhiqin
Zhang, Yonggang
Li, Chenxin
Cheung, Yiu-ming
Han, Bo
Yuan, Yixuan
contents Federated Learning (FL) confronts a significant challenge known as data heterogeneity, which impairs model performance and convergence. Existing methods have made notable progress in addressing this issue. However, improving performance in certain heterogeneity scenarios remains an overlooked question: \textit{How robust are these methods to deploy under diverse heterogeneity scenarios?} To answer this, we conduct comprehensive evaluations across varied heterogeneity scenarios, showing that most existing methods exhibit limited robustness. Meanwhile, insights from these experiments highlight that sharing statistical information can mitigate heterogeneity by enabling clients to update with a global perspective. Motivated by this, we propose \textbf{FedGPS} (\textbf{Fed}erated \textbf{G}oal-\textbf{P}ath \textbf{S}ynergy), a novel framework that seamlessly integrates statistical distribution and gradient information from others. Specifically, FedGPS statically modifies each client's learning objective to implicitly model the global data distribution using surrogate information, while dynamically adjusting local update directions with gradient information from other clients at each round. Extensive experiments show that FedGPS outperforms state-of-the-art methods across diverse heterogeneity scenarios, validating its effectiveness and robustness. The code is available at: https://github.com/CUHK-AIM-Group/FedGPS.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20250
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning
Yang, Zhiqin
Zhang, Yonggang
Li, Chenxin
Cheung, Yiu-ming
Han, Bo
Yuan, Yixuan
Machine Learning
Federated Learning (FL) confronts a significant challenge known as data heterogeneity, which impairs model performance and convergence. Existing methods have made notable progress in addressing this issue. However, improving performance in certain heterogeneity scenarios remains an overlooked question: \textit{How robust are these methods to deploy under diverse heterogeneity scenarios?} To answer this, we conduct comprehensive evaluations across varied heterogeneity scenarios, showing that most existing methods exhibit limited robustness. Meanwhile, insights from these experiments highlight that sharing statistical information can mitigate heterogeneity by enabling clients to update with a global perspective. Motivated by this, we propose \textbf{FedGPS} (\textbf{Fed}erated \textbf{G}oal-\textbf{P}ath \textbf{S}ynergy), a novel framework that seamlessly integrates statistical distribution and gradient information from others. Specifically, FedGPS statically modifies each client's learning objective to implicitly model the global data distribution using surrogate information, while dynamically adjusting local update directions with gradient information from other clients at each round. Extensive experiments show that FedGPS outperforms state-of-the-art methods across diverse heterogeneity scenarios, validating its effectiveness and robustness. The code is available at: https://github.com/CUHK-AIM-Group/FedGPS.
title FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning
topic Machine Learning
url https://arxiv.org/abs/2510.20250