Guardado en:
Detalles Bibliográficos
Autores principales: Xu, Lihan, Dong, Yanjie, Wang, Gang, Zeng, Runhao, Fan, Xiaoyi, Hu, Xiping
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.02657
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915597090029568
author Xu, Lihan
Dong, Yanjie
Wang, Gang
Zeng, Runhao
Fan, Xiaoyi
Hu, Xiping
author_facet Xu, Lihan
Dong, Yanjie
Wang, Gang
Zeng, Runhao
Fan, Xiaoyi
Hu, Xiping
contents We investigate robust federated learning, where a group of workers collaboratively train a shared model under the orchestration of a central server in the presence of Byzantine adversaries capable of arbitrary and potentially malicious behaviors. To simultaneously enhance communication efficiency and robustness against such adversaries, we propose a Byzantine-resilient Nesterov-Accelerated Federated Learning (Byrd-NAFL) algorithm. Byrd-NAFL seamlessly integrates Nesterov's momentum into the federated learning process alongside Byzantine-resilient aggregation rules to achieve fast and safeguarding convergence against gradient corruption. We establish a finite-time convergence guarantee for Byrd-NAFL under non-convex and smooth loss functions with relaxed assumption on the aggregated gradients. Extensive numerical experiments validate the effectiveness of Byrd-NAFL and demonstrate the superiority over existing benchmarks in terms of convergence speed, accuracy, and resilience to diverse Byzantine attack strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2511_02657
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Nesterov-Accelerated Robust Federated Learning Over Byzantine Adversaries
Xu, Lihan
Dong, Yanjie
Wang, Gang
Zeng, Runhao
Fan, Xiaoyi
Hu, Xiping
Machine Learning
We investigate robust federated learning, where a group of workers collaboratively train a shared model under the orchestration of a central server in the presence of Byzantine adversaries capable of arbitrary and potentially malicious behaviors. To simultaneously enhance communication efficiency and robustness against such adversaries, we propose a Byzantine-resilient Nesterov-Accelerated Federated Learning (Byrd-NAFL) algorithm. Byrd-NAFL seamlessly integrates Nesterov's momentum into the federated learning process alongside Byzantine-resilient aggregation rules to achieve fast and safeguarding convergence against gradient corruption. We establish a finite-time convergence guarantee for Byrd-NAFL under non-convex and smooth loss functions with relaxed assumption on the aggregated gradients. Extensive numerical experiments validate the effectiveness of Byrd-NAFL and demonstrate the superiority over existing benchmarks in terms of convergence speed, accuracy, and resilience to diverse Byzantine attack strategies.
title Nesterov-Accelerated Robust Federated Learning Over Byzantine Adversaries
topic Machine Learning
url https://arxiv.org/abs/2511.02657