Saved in:
Bibliographic Details
Main Authors: Zhang, Rongyu, Chen, Yun, Wu, Chenrui, Wang, Fangxin, Li, Bo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.06413
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911872973799424
author Zhang, Rongyu
Chen, Yun
Wu, Chenrui
Wang, Fangxin
Li, Bo
author_facet Zhang, Rongyu
Chen, Yun
Wu, Chenrui
Wang, Fangxin
Li, Bo
contents Federated learning (FL) offers a privacy-centric distributed learning framework, enabling model training on individual clients and central aggregation without necessitating data exchange. Nonetheless, FL implementations often suffer from non-i.i.d. and long-tailed class distributions across mobile applications, e.g., autonomous vehicles, which leads models to overfitting as local training may converge to sub-optimal. In our study, we explore the impact of data heterogeneity on model bias and introduce an innovative personalized FL framework, Multi-level Personalized Federated Learning (MuPFL), which leverages the hierarchical architecture of FL to fully harness computational resources at various levels. This framework integrates three pivotal modules: Biased Activation Value Dropout (BAVD) to mitigate overfitting and accelerate training; Adaptive Cluster-based Model Update (ACMU) to refine local models ensuring coherent global aggregation; and Prior Knowledge-assisted Classifier Fine-tuning (PKCF) to bolster classification and personalize models in accord with skewed local data with shared knowledge. Extensive experiments on diverse real-world datasets for image classification and semantic segmentation validate that MuPFL consistently outperforms state-of-the-art baselines, even under extreme non-i.i.d. and long-tail conditions, which enhances accuracy by as much as 7.39% and accelerates training by up to 80% at most, marking significant advancements in both efficiency and effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06413
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Data
Zhang, Rongyu
Chen, Yun
Wu, Chenrui
Wang, Fangxin
Li, Bo
Artificial Intelligence
Federated learning (FL) offers a privacy-centric distributed learning framework, enabling model training on individual clients and central aggregation without necessitating data exchange. Nonetheless, FL implementations often suffer from non-i.i.d. and long-tailed class distributions across mobile applications, e.g., autonomous vehicles, which leads models to overfitting as local training may converge to sub-optimal. In our study, we explore the impact of data heterogeneity on model bias and introduce an innovative personalized FL framework, Multi-level Personalized Federated Learning (MuPFL), which leverages the hierarchical architecture of FL to fully harness computational resources at various levels. This framework integrates three pivotal modules: Biased Activation Value Dropout (BAVD) to mitigate overfitting and accelerate training; Adaptive Cluster-based Model Update (ACMU) to refine local models ensuring coherent global aggregation; and Prior Knowledge-assisted Classifier Fine-tuning (PKCF) to bolster classification and personalize models in accord with skewed local data with shared knowledge. Extensive experiments on diverse real-world datasets for image classification and semantic segmentation validate that MuPFL consistently outperforms state-of-the-art baselines, even under extreme non-i.i.d. and long-tail conditions, which enhances accuracy by as much as 7.39% and accelerates training by up to 80% at most, marking significant advancements in both efficiency and effectiveness.
title Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Data
topic Artificial Intelligence
url https://arxiv.org/abs/2405.06413