FLARE: A New Federated Learning Framework with Adjustable Learning Rates over Resource-Constrained Wireless Networks
Not on the map. Why?
Abstract (arXiv)
Wireless federated learning (WFL) suffers from heterogeneity prevailing in the data distributions, computing powers, and channel conditions of participating devices. This paper presents a new Federated Learning with Adjusted leaRning ratE (FLARE) framework to mitigate the impact of the heterogeneity. The key idea is to allow the participating devices to adjust their individual learning rates and local training iterations, adapting to their instantaneous computing powers. The convergence upper bound of FLARE is established rigorously under a general setting with non-convex models in the presence of non-i.i.d. datasets and imbalanced computing powers. By minimizing the upper bound, we further optimize the scheduling of FLARE to exploit the channel heterogeneity. A nested problem structure is revealed to facilitate iteratively allocating the bandwidth with binary search and selecting devices with a new greedy method. A linear problem structure is also identified and a low-complexity linear programming scheduling policy is designed when training models have large Lipschitz constants. Experiments demonstrate that FLARE consistently outperforms the baselines in test accuracy, and converges much faster with the proposed scheduling policy.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 38 of its 52 references that are in the map. First posted on arXiv 23 Apr 2024.
Builds on
38 of 52 references.
References · 38
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2013Intriguing properties of neural networkscited by 5,155
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
- 2018Federated Learning with Non-IID Datacited by 1,108
- 2021Model-Contrastive Federated Learningcited by 766
- 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
- 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 352
- 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 337
26 more
- 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 278
- 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 263
- 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 193
- 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
- 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
- 2019Federated Learning for Wireless Communications: Motivation, Opportunities and Challengescited by 129
- 2021Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradientscited by 123
- 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 103
- 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
- 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
- 2019Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation Systemcited by 79
- 2020Convergence of Update Aware Device Scheduling for Federated Learning at the Wireless Edgecited by 71
- 2019The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squarescited by 68
- 2021Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Samplingcited by 66
- 2020Scheduling for Cellular Federated Edge Learning with Importance and Channel Awarenesscited by 62
- 2020Fast-Convergent Federated Learningcited by 61
- 2021The Road Towards 6G: A Comprehensive Surveycited by 40
- 2021Learning Rate Optimization for Federated Learning Exploiting Over-the-air Computationcited by 29
- 2021Cost-Effective Federated Learning in Mobile Edge Networkscited by 25
- 2020Distributed Machine Learning for Wireless Communication Networks: Techniques, Architectures, and Applicationscited by 21
- 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directionscited by 21
- 2022Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networkscited by 20
- 2020Communication-Efficient Massive UAV Online Path Control: Federated Learning Meets Mean-Field Game Theorycited by 16
- 2023OFDMA-F2L: Federated Learning With Flexible Aggregation Over an OFDMA Air Interfacecited by 6
- 2018Learning and Management for Internet-of-Things: Accounting for Adaptivity and Scalabilitycited by 5
- 2023Multi-Carrier NOMA-Empowered Wireless Federated Learning with Optimal Power and Bandwidth Allocationcited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.