FedCust: Offloading hyperparameter customization for federated learning
Authors:
- Syed ZawadSZSyed Zawad
- Xiaolong MaXMXiaolong Ma
- Jun YiJYJun Yi
- Cheng LiCLCheng Li
- Minjia ZhangMZMinjia Zhang
- Lei YangLYLei Yang
- Feng YanFYFeng Yan
- Yuxiong HeYHYuxiong He
- 16 November 2024
- journal article
- research article
- Published by Elsevier in Performance Evaluation
- Vol. 167
Abstract
No abstract availableKeywords
Funding Information
- National Science Foundation (CAREER-2305491)
This publication has 18 references indexed in Scilit:
- Communication-Efficient Federated Learning for Resource-Constrained Edge DevicesIEEE Transactions on Machine Learning in Communications and Networking, 2023
- Efficient and flexible management for industrial Internet of Things: A federated learning approachComputer Networks, 2021
- Federated Learning for Internet of Things: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2021
- Federated Learning: A Survey on Enabling Technologies, Protocols, and ApplicationsIEEE Access, 2020
- Federated Learning: Challenges, Methods, and Future DirectionsIEEE Signal Processing Magazine, 2020
- Federated Learning in Mobile Edge Networks: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2020
- Federated Learning With Cooperating Devices: A Consensus Approach for Massive IoT NetworksIEEE Internet of Things Journal, 2020
- Adaptive Federated Learning in Resource Constrained Edge Computing SystemsIEEE Journal on Selected Areas in Communications, 2019
- Convergence properties of the expected improvement algorithm with fixed mean and covariance functionsJournal of Statistical Planning and Inference, 2010
- The Divergence and Bhattacharyya Distance Measures in Signal SelectionIEEE Transactions on Communications, 1967