Device scheduling and bandwidth allocation for federated learning over wireless networks
Federated Learning (FL) has been widely used to train shared machine learning models while addressing the privacy concerns. When deployed in wireless networks, bandwidth resources limitation is a key issue, thereby necessitating device scheduling and bandwidth allocation. It is challenging to carry...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/176958 |
| _version_ | 1811681194181394432 |
|---|---|
| author | Zhang, Tinghao Lam, Kwok-Yan Zhao, Jun |
| author2 | College of Computing and Data Science |
| author_facet | College of Computing and Data Science Zhang, Tinghao Lam, Kwok-Yan Zhao, Jun |
| author_sort | Zhang, Tinghao |
| collection | NTU |
| description | Federated Learning (FL) has been widely used to train shared machine learning models while addressing the privacy concerns. When deployed in wireless networks, bandwidth resources limitation is a key issue, thereby necessitating device scheduling and bandwidth allocation. It is challenging to carry out device scheduling due to the large combinatorial search space. Besides, the heterogeneous computing capabilities and uncertain channel states of wireless devices complicate the design of a bandwidth allocation method. In this paper, we propose a joint device scheduling and bandwidth allocation framework for implementing FL in wireless networks. Specifically, deep reinforcement learning (DRL) is employed to conduct device scheduling. To this end, the state space, action space, and reward function of DRL are carefully defined for a typical FL system. Long short-term memory (LSTM) is adopted as the DRL agent to analyze the sequential input data. Given the scheduled devices of each global iteration, the proposed bandwidth allocation method aims to minimize the weighted sum of the time delay and energy consumption. Numerical experiments on both independent and identically distributed (IID) and non-IID datasets demonstrate that the proposed framework enables FL to reach the desired accuracy with low time delay and energy consumption. |
| first_indexed | 2024-10-01T03:37:04Z |
| format | Conference Paper |
| id | ntu-10356/176958 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:37:04Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1769582024-05-20T02:44:59Z Device scheduling and bandwidth allocation for federated learning over wireless networks Zhang, Tinghao Lam, Kwok-Yan Zhao, Jun College of Computing and Data Science School of Computer Science and Engineering 2023 10th International Conference on ICT for Smart Society (ICISS) Computer and Information Science Training Energy consumption Federated Learning (FL) has been widely used to train shared machine learning models while addressing the privacy concerns. When deployed in wireless networks, bandwidth resources limitation is a key issue, thereby necessitating device scheduling and bandwidth allocation. It is challenging to carry out device scheduling due to the large combinatorial search space. Besides, the heterogeneous computing capabilities and uncertain channel states of wireless devices complicate the design of a bandwidth allocation method. In this paper, we propose a joint device scheduling and bandwidth allocation framework for implementing FL in wireless networks. Specifically, deep reinforcement learning (DRL) is employed to conduct device scheduling. To this end, the state space, action space, and reward function of DRL are carefully defined for a typical FL system. Long short-term memory (LSTM) is adopted as the DRL agent to analyze the sequential input data. Given the scheduled devices of each global iteration, the proposed bandwidth allocation method aims to minimize the weighted sum of the time delay and energy consumption. Numerical experiments on both independent and identically distributed (IID) and non-IID datasets demonstrate that the proposed framework enables FL to reach the desired accuracy with low time delay and energy consumption. Info-communications Media Development Authority (IMDA) National Research Foundation (NRF) Submitted/Accepted version This research is supported by the National Research Foundation, Singapore and Infocomm Media Development Authority under its Future Communications Research & Development Programme. 2024-05-20T02:44:59Z 2024-05-20T02:44:59Z 2023 Conference Paper Zhang, T., Lam, K. & Zhao, J. (2023). Device scheduling and bandwidth allocation for federated learning over wireless networks. 2023 10th International Conference on ICT for Smart Society (ICISS). https://dx.doi.org/10.1109/ICISS59129.2023.10291589 9798350339543 https://hdl.handle.net/10356/176958 10.1109/ICISS59129.2023.10291589 2-s2.0-85177469977 en © 2023 IEEE. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1109/ICISS59129.2023.10291589. application/pdf |
| spellingShingle | Computer and Information Science Training Energy consumption Zhang, Tinghao Lam, Kwok-Yan Zhao, Jun Device scheduling and bandwidth allocation for federated learning over wireless networks |
| title | Device scheduling and bandwidth allocation for federated learning over wireless networks |
| title_full | Device scheduling and bandwidth allocation for federated learning over wireless networks |
| title_fullStr | Device scheduling and bandwidth allocation for federated learning over wireless networks |
| title_full_unstemmed | Device scheduling and bandwidth allocation for federated learning over wireless networks |
| title_short | Device scheduling and bandwidth allocation for federated learning over wireless networks |
| title_sort | device scheduling and bandwidth allocation for federated learning over wireless networks |
| topic | Computer and Information Science Training Energy consumption |
| url | https://hdl.handle.net/10356/176958 |
| work_keys_str_mv | AT zhangtinghao deviceschedulingandbandwidthallocationforfederatedlearningoverwirelessnetworks AT lamkwokyan deviceschedulingandbandwidthallocationforfederatedlearningoverwirelessnetworks AT zhaojun deviceschedulingandbandwidthallocationforfederatedlearningoverwirelessnetworks |