Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Hong, Shan, Liren, Bao, Han, You, Ronghui, Yi, Yuhao, Lv, Jiancheng
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2408.04963
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916632385814528
author Liu, Hong
Shan, Liren
Bao, Han
You, Ronghui
Yi, Yuhao
Lv, Jiancheng
author_facet Liu, Hong
Shan, Liren
Bao, Han
You, Ronghui
Yi, Yuhao
Lv, Jiancheng
contents Federated learning is often used in environments with many unverified participants. Therefore, federated learning under adversarial attacks receives significant attention. This paper proposes an algorithmic framework for list-decodable federated learning, where a central server maintains a list of models, with at least one guaranteed to perform well. The framework has no strict restriction on the fraction of honest workers, extending the applicability of Byzantine federated learning to the scenario with more than half adversaries. Under proper assumptions on the loss function, we prove a convergence theorem for our method. Experimental results, including image classification tasks with both convex and non-convex losses, demonstrate that the proposed algorithm can withstand the malicious majority under various attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2408_04963
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LiD-FL: Towards List-Decodable Federated Learning
Liu, Hong
Shan, Liren
Bao, Han
You, Ronghui
Yi, Yuhao
Lv, Jiancheng
Machine Learning
Federated learning is often used in environments with many unverified participants. Therefore, federated learning under adversarial attacks receives significant attention. This paper proposes an algorithmic framework for list-decodable federated learning, where a central server maintains a list of models, with at least one guaranteed to perform well. The framework has no strict restriction on the fraction of honest workers, extending the applicability of Byzantine federated learning to the scenario with more than half adversaries. Under proper assumptions on the loss function, we prove a convergence theorem for our method. Experimental results, including image classification tasks with both convex and non-convex losses, demonstrate that the proposed algorithm can withstand the malicious majority under various attacks.
title LiD-FL: Towards List-Decodable Federated Learning
topic Machine Learning
url https://arxiv.org/abs/2408.04963