A DQN-Based Multi-Objective Participant Selection for Efficient Federated Learning
Future Internet · 08.06.2023 · 15 (6) · 209
DOI: 10.3390/fi15060209 ↗Kurz gefasst
Fachartikel in der Zeitschrift Future Internet, online erschienen am 08.06.2023. Verfasst von Tongyang Xu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Heilongjiang Province of China, Key Research and Development Program Heilongjiang Province of China.
Abstract (Originalsprache)
As a new distributed machine learning (ML) approach, federated learning (FL) shows great potential to preserve data privacy by enabling distributed data owners to collaboratively build a global model without sharing their raw data. However, the heterogeneity in terms of data distribution and hardware configurations make it hard to select participants from the thousands of nodes. In this paper, we propose a multi-objective node selection approach to improve time-to-accuracy performance while resisting malicious nodes. We firstly design a deep reinforcement learning-assisted FL framework. Then, the problem of multi-objective node selection under this framework is formulated as a Markov decision process (MDP), which aims to reduce the training time and improve model accuracy simultaneously. Finally, a Deep Q-Network (DQN)-based algorithm is proposed to efficiently solve the optimal set of participants for each iteration. Simulation results show that the proposed method not only significantly improves the accuracy and training speed of FL, but also has stronger robustness to resist malicious nodes.
Förderung
- Natural Science Foundation of Heilongjiang Province of China
- Key Research and Development Program Heilongjiang Province of China
Zitieren
APA
Xu, T., Liu, Y., Ma, Z., Huang, Y., & Liu, P. (2023). A DQN-Based Multi-Objective Participant Selection for Efficient Federated Learning. Future Internet, 15(6), 209. https://doi.org/10.3390/fi15060209
Vancouver
Xu T, Liu Y, Ma Z, Huang Y, Liu P. A DQN-Based Multi-Objective Participant Selection for Efficient Federated Learning. Future Internet. 2023;15(6):209. doi:10.3390/fi15060209
BibTeX
@article{Xu2023,
author = {Xu, Tongyang and Liu, Yuan and Ma, Zhaotai and Huang, Yiqiang and Liu, Peng},
title = {A DQN-Based Multi-Objective Participant Selection for Efficient Federated Learning},
journal = {Future Internet},
year = {2023},
volume = {15},
number = {6},
pages = {209},
doi = {10.3390/fi15060209}
}
EUVIMED