Saved in:
Bibliographic Details
Main Authors: Yang, Changxin, Zhu, Zhongyi, Lian, Heng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.10576
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908588942819328
author Yang, Changxin
Zhu, Zhongyi
Lian, Heng
author_facet Yang, Changxin
Zhu, Zhongyi
Lian, Heng
contents Federated learning has attracted significant attention as a privacy-preserving framework for training personalised models on multi-source heterogeneous data. However, most existing approaches are unable to handle scenarios where subgroup structures coexist alongside within-group heterogeneity. In this paper, we propose a federated learning algorithm that addresses general heterogeneity through adaptive clustering. Specifically, our method partitions tasks into subgroups to address substantial between-group differences while enabling efficient information sharing among similar tasks within each group. Furthermore, we integrate the Huber loss and Iterative Hard Thresholding (IHT) to tackle the challenges of high dimensionality and heavy-tailed distributions. Theoretically, we establish convergence guarantees, derive non-asymptotic error bounds, and provide recovery guarantees for the latent cluster structure. Extensive simulation studies and real-data applications further demonstrate the effectiveness and adaptability of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10576
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Clustered Federated Learning for Heterogeneous High-dimensional Data
Yang, Changxin
Zhu, Zhongyi
Lian, Heng
Methodology
Federated learning has attracted significant attention as a privacy-preserving framework for training personalised models on multi-source heterogeneous data. However, most existing approaches are unable to handle scenarios where subgroup structures coexist alongside within-group heterogeneity. In this paper, we propose a federated learning algorithm that addresses general heterogeneity through adaptive clustering. Specifically, our method partitions tasks into subgroups to address substantial between-group differences while enabling efficient information sharing among similar tasks within each group. Furthermore, we integrate the Huber loss and Iterative Hard Thresholding (IHT) to tackle the challenges of high dimensionality and heavy-tailed distributions. Theoretically, we establish convergence guarantees, derive non-asymptotic error bounds, and provide recovery guarantees for the latent cluster structure. Extensive simulation studies and real-data applications further demonstrate the effectiveness and adaptability of our approach.
title Robust Clustered Federated Learning for Heterogeneous High-dimensional Data
topic Methodology
url https://arxiv.org/abs/2510.10576