Toward Dynamic Resource Allocation and Client Scheduling in Hierarchical Federated Learning: A Two-Phase Deep Reinforcement Learning Approach
IEEE Transactions on Communications · 2024-12 · 72 (12) · 7798-7813
DOI: 10.1109/tcomm.2024.3420733 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Communications, 2024-12. Verfasst von Xiaojing Chen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Innovation Program of Shanghai Municipal Science and Technology Commission, Program of Hebei Key Laboratory of Advanced Laser Technology and Equipment.
Abstract (Originalsprache)
Federated learning (FL) is a viable technique to train a shared machine learning model without sharing data. Hierarchical FL (HFL) system has yet to be studied regrading its multiple levels of energy, computation, communication, and client scheduling, especially when it comes to clients relying on energy harvesting to power their operations. This paper presents a new two-phase deep deterministic policy gradient (DDPG) framework, referred to as “TP-DDPG”, to balance online the learning delay and model accuracy of an FL process in an energy harvesting-powered HFL system. The key idea is that we divide optimization decisions into two groups, and employ DDPG to learn one group in the first phase, while interpreting the other group as part of the environment to provide rewards for training the DDPG in the second phase. Specifically, the DDPG learns the selection of participating clients, and their CPU configurations and the transmission powers. A new straggler-aware client association and bandwidth allocation (SCABA) algorithm efficiently optimizes the other decisions and evaluates the reward for the DDPG. Experiments demonstrate that with substantially reduced number of learnable parameters, the TP-DDPG can quickly converge to effective polices that can shorten the training time of HFL by 39.4% compared to its benchmarks, when the required test accuracy of HFL is 0.9.
Förderung
- National Key Research and Development Program of China
- Innovation Program of Shanghai Municipal Science and Technology Commission
- Program of Hebei Key Laboratory of Advanced Laser Technology and Equipment
- National High Quality Program
- Shanghai Rising-Star Program
Zitieren
APA
Chen, X., Li, Z., Ni, W., Wang, X., Zhang, S., Sun, Y., Xu, S., & Pei, Q. (2024). Toward Dynamic Resource Allocation and Client Scheduling in Hierarchical Federated Learning: A Two-Phase Deep Reinforcement Learning Approach. IEEE Transactions on Communications, 72(12), 7798-7813. https://doi.org/10.1109/tcomm.2024.3420733
Vancouver
Chen X, Li Z, Ni W, Wang X, Zhang S, Sun Y, et al. Toward Dynamic Resource Allocation and Client Scheduling in Hierarchical Federated Learning: A Two-Phase Deep Reinforcement Learning Approach. IEEE Transactions on Communications. 2024;72(12):7798-7813. doi:10.1109/tcomm.2024.3420733
BibTeX
@article{Chen2024,
author = {Chen, Xiaojing and Li, Zhenyuan and Ni, Wei and Wang, Xin and Zhang, Shunqing and Sun, Yanzan and Xu, Shugong and Pei, Qingqi},
title = {Toward Dynamic Resource Allocation and Client Scheduling in Hierarchical Federated Learning: A Two-Phase Deep Reinforcement Learning Approach},
journal = {IEEE Transactions on Communications},
year = {2024},
volume = {72},
number = {12},
pages = {7798--7813},
doi = {10.1109/tcomm.2024.3420733}
}
EUVIMED