MAB-Based Online Client Scheduling for Decentralized Federated Learning in the IoT
Different from conventional federated learning (FL), which relies on a central server for model aggregation, decentralized FL (DFL) exchanges models among edge servers, thus improving the robustness and scalability. When deploying DFL into the Internet of Things (IoT), limited wireless resources can...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/27/4/439 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850144883494354944 |
|---|---|
| author | Zhenning Chen Xinyu Zhang Siyang Wang Youren Wang |
| author_facet | Zhenning Chen Xinyu Zhang Siyang Wang Youren Wang |
| author_sort | Zhenning Chen |
| collection | DOAJ |
| description | Different from conventional federated learning (FL), which relies on a central server for model aggregation, decentralized FL (DFL) exchanges models among edge servers, thus improving the robustness and scalability. When deploying DFL into the Internet of Things (IoT), limited wireless resources cannot provide simultaneous access to massive devices. One must perform client scheduling to balance the convergence rate and model accuracy. However, the heterogeneity of computing and communication resources across client devices, combined with the time-varying nature of wireless channels, makes it challenging to estimate accurately the delay associated with client participation during the scheduling process. To address this issue, we investigate the client scheduling and resource optimization problem in DFL without prior client information. Specifically, the considered problem is reformulated as a multi-armed bandit (MAB) program, and an online learning algorithm that utilizes contextual multi-arm slot machines for client delay estimation and scheduling is proposed. Through theoretical analysis, this algorithm can achieve asymptotic optimal performance in theory. The experimental results show that the algorithm can make asymptotic optimal client selection decisions, and this method is superior to existing algorithms in reducing the cumulative delay of the system. |
| format | Article |
| id | doaj-art-802d8e2fb27845edb482c3ae36aee546 |
| institution | OA Journals |
| issn | 1099-4300 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj-art-802d8e2fb27845edb482c3ae36aee5462025-08-20T02:28:14ZengMDPI AGEntropy1099-43002025-04-0127443910.3390/e27040439MAB-Based Online Client Scheduling for Decentralized Federated Learning in the IoTZhenning Chen0Xinyu Zhang1Siyang Wang2Youren Wang3College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaSchool of Computer Science and Technology, Nanjing University of Posts and Telecommunications, Nanjing 210049, ChinaJiangsu Key Laboratory of Wireless Communications, Nanjing University of Posts and Telecommunications, Nanjing 210049, ChinaCollege of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaDifferent from conventional federated learning (FL), which relies on a central server for model aggregation, decentralized FL (DFL) exchanges models among edge servers, thus improving the robustness and scalability. When deploying DFL into the Internet of Things (IoT), limited wireless resources cannot provide simultaneous access to massive devices. One must perform client scheduling to balance the convergence rate and model accuracy. However, the heterogeneity of computing and communication resources across client devices, combined with the time-varying nature of wireless channels, makes it challenging to estimate accurately the delay associated with client participation during the scheduling process. To address this issue, we investigate the client scheduling and resource optimization problem in DFL without prior client information. Specifically, the considered problem is reformulated as a multi-armed bandit (MAB) program, and an online learning algorithm that utilizes contextual multi-arm slot machines for client delay estimation and scheduling is proposed. Through theoretical analysis, this algorithm can achieve asymptotic optimal performance in theory. The experimental results show that the algorithm can make asymptotic optimal client selection decisions, and this method is superior to existing algorithms in reducing the cumulative delay of the system.https://www.mdpi.com/1099-4300/27/4/439decentralized federated learningclient schedulingmulti-armed bandit |
| spellingShingle | Zhenning Chen Xinyu Zhang Siyang Wang Youren Wang MAB-Based Online Client Scheduling for Decentralized Federated Learning in the IoT Entropy decentralized federated learning client scheduling multi-armed bandit |
| title | MAB-Based Online Client Scheduling for Decentralized Federated Learning in the IoT |
| title_full | MAB-Based Online Client Scheduling for Decentralized Federated Learning in the IoT |
| title_fullStr | MAB-Based Online Client Scheduling for Decentralized Federated Learning in the IoT |
| title_full_unstemmed | MAB-Based Online Client Scheduling for Decentralized Federated Learning in the IoT |
| title_short | MAB-Based Online Client Scheduling for Decentralized Federated Learning in the IoT |
| title_sort | mab based online client scheduling for decentralized federated learning in the iot |
| topic | decentralized federated learning client scheduling multi-armed bandit |
| url | https://www.mdpi.com/1099-4300/27/4/439 |
| work_keys_str_mv | AT zhenningchen mabbasedonlineclientschedulingfordecentralizedfederatedlearningintheiot AT xinyuzhang mabbasedonlineclientschedulingfordecentralizedfederatedlearningintheiot AT siyangwang mabbasedonlineclientschedulingfordecentralizedfederatedlearningintheiot AT yourenwang mabbasedonlineclientschedulingfordecentralizedfederatedlearningintheiot |