Literature Database Entry

tao2026byzantine-resilient

Youming Tao, Zuyuan Zhang, Di Wang, Dongxiao Yu, Xiuzhen Cheng and Falko Dressler, "Byzantine-Resilient Federated Learning under Heterogeneity and Heavy Tails," IEEE Transactions on Networking, April 2026. (online first)

Abstract

Byzantine resilience is essential in federated learning (FL) to safeguard model training from malicious or faulty participants. However, existing Byzantine-resilient methods struggle when faced with heavy-tailed gradient noise, a common challenge in heterogeneous environments. In this work, we propose a Byzantine-resilient FL framework specifically designed to handle both heterogeneity and heavy-tailed noise. Our approach builds on robust distributed stochastic heavy-ball optimization, incorporating update normalization and gradient/momentum clipping to mitigate the effects of heavy-tailed noise. We establish the first high-probability convergence guarantees for Byzantine-resilient FL under these conditions, showing that our algorithms achieve optimal Byzantine resilience and align with known lower bounds. Additionally, we introduce an efficient variant of the nearest neighbor mixing technique, leveraging random projections to significantly reduce computational costs in high-dimensional settings. Through rigorous theoretical analysis and extensive empirical evaluations, we demonstrate that our methods outperform existing approaches in robustness against both Byzantine failures and heavy-tailed noise.

Quick access

Original Version DOI (at publishers web site)
Authors' Version PDF (PDF on this web site)
BibTeX BibTeX

Contact

Youming Tao
Zuyuan Zhang
Di Wang
Dongxiao Yu
Xiuzhen Cheng
Falko Dressler

BibTeX reference

@article{tao2026byzantine-resilient,
    author = {Tao, Youming and Zhang, Zuyuan and Wang, Di and Yu, Dongxiao and Cheng, Xiuzhen and Dressler, Falko},
    doi = {10.1109/TON.2026.3686661},
    note = {to appear},
    title = {{Byzantine-Resilient Federated Learning under Heterogeneity and Heavy Tails}},
    journal = {IEEE Transactions on Networking},
    issn = {2998-4157},
    publisher = {IEEE},
    month = {4},
    year = {2026},
   }
   
   

Copyright notice

Links to final or draft versions of papers are presented here to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted or distributed for commercial purposes without the explicit permission of the copyright holder.

The following applies to all papers listed above that have IEEE copyrights: Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

The following applies to all papers listed above that are in submission to IEEE conference/workshop proceedings or journals: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.

The following applies to all papers listed above that have ACM copyrights: ACM COPYRIGHT NOTICE. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, to republish, to post on servers, or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Publications Dept., ACM, Inc., fax +1 (212) 869-0481, or permissions@acm.org.

The following applies to all SpringerLink papers listed above that have Springer Science+Business Media copyrights: The original publication is available at www.springerlink.com.

This page was automatically generated using BibDB and bib2web.

Last modified: 2026-04-28