TY - GEN
T1 - A Federated Learning Client Selection Method via Multi-Task Deep Reinforcement Learning
AU - Hou, Le
AU - Nie, Laisen
AU - Deng, Xinyang
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Federated Learning (FL) is a privacy-preserving paradigm for training machine learning (ML) models, crucial for data privacy and security protection.It has garnered significant attention from both industry and academia.Typically, clients are selected randomly for training and model aggregation in FL scenarios.However, heterogeneity in data distribution and hardware among devices leads to problems such as slow model convergence, low accuracy, and high computational overhead.To address the issues of statistical heterogeneity and system heterogeneity in FL, this paper proposes an intelligent client selection framework via multi-task deep reinforcement learning (DRL).Additionally, two reward functions are introduced to alleviate the heterogeneity problem by maximizing model performance and minimizing system latency.Experimental results on MNIST and CIFAR-10 datasets demonstrate the effectiveness of the proposed method.
AB - Federated Learning (FL) is a privacy-preserving paradigm for training machine learning (ML) models, crucial for data privacy and security protection.It has garnered significant attention from both industry and academia.Typically, clients are selected randomly for training and model aggregation in FL scenarios.However, heterogeneity in data distribution and hardware among devices leads to problems such as slow model convergence, low accuracy, and high computational overhead.To address the issues of statistical heterogeneity and system heterogeneity in FL, this paper proposes an intelligent client selection framework via multi-task deep reinforcement learning (DRL).Additionally, two reward functions are introduced to alleviate the heterogeneity problem by maximizing model performance and minimizing system latency.Experimental results on MNIST and CIFAR-10 datasets demonstrate the effectiveness of the proposed method.
KW - client selection
KW - federated learning
KW - multi-task deep reinforcement learning
KW - statistical heterogeneity
KW - system heterogeneity
UR - http://www.scopus.com/inward/record.url?scp=85218071662&partnerID=8YFLogxK
U2 - 10.1109/ICUS61736.2024.10840140
DO - 10.1109/ICUS61736.2024.10840140
M3 - 会议稿件
AN - SCOPUS:85218071662
T3 - Proceedings of 2024 IEEE International Conference on Unmanned Systems, ICUS 2024
SP - 1357
EP - 1362
BT - Proceedings of 2024 IEEE International Conference on Unmanned Systems, ICUS 2024
A2 - Song, Rong
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE International Conference on Unmanned Systems, ICUS 2024
Y2 - 18 October 2024 through 20 October 2024
ER -