Revisiting Communication-Efficient Federated Learning with Balanced Global and Local Updates
Not on the map. Why?
Abstract (arXiv)
In federated learning (FL), a number of devices train their local models and upload the corresponding parameters or gradients to the base station (BS) to update the global model while protecting their data privacy. However, due to the limited computation and communication resources, the number of local trainings (a.k.a. local update) and that of aggregations (a.k.a. global update) need to be carefully chosen. In this paper, we investigate and analyze the optimal trade-off between the number of local trainings and that of global aggregations to speed up the convergence and enhance the prediction accuracy over the existing works. Our goal is to minimize the global loss function under both the delay and the energy consumption constraints. In order to make the optimization problem tractable, we derive a new and tight upper bound on the loss function, which allows us to obtain closed-form expressions for the number of local trainings and that of global aggregations. Simulation results show that our proposed scheme can achieve a better performance in terms of the prediction accuracy, and converge much faster than the baseline schemes.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 35 references that are in the map. First posted on arXiv 3 May 2022.
Builds on
27 of 35 references.
References · 27
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2019Deep Leakage from Gradientscited by 1,021
- 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
- 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
- 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
- 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
- 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 263
- 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
- 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
- 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
15 more
- 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
- 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
- 2020Convergence Time Optimization for Federated Learning over Wireless Networkscited by 81
- 2020Scheduling for Cellular Federated Edge Learning with Importance and Channel Awarenesscited by 62
- 2020Cost-Effective Federated Learning Designcited by 62
- 2019Energy-Efficient Radio Resource Allocation for Federated Edge Learningcited by 39
- 2019Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networkscited by 39
- 2019Robust Federated Learning with Noisy Communicationcited by 34
- 2021Convergence Analysis and System Design for Federated Learning over Wireless Networkscited by 25
- 2021FedMatch: Federated Learning Over Heterogeneous Question Answering Datacited by 23
- 2021Federated Learning over Energy Harvesting Wireless Networkscited by 17
- 2020Budgeted Online Selection of Candidate IoT Clients to Participate in Federated Learningcited by 14
- 2016A Unified Coding Framework for Distributed Computing with Straggling Serverscited by 8
- 2020D2D-Enabled Data Sharing for Distributed Machine Learning at Wireless Network Edgecited by 5
- 2020Jointly Optimizing Dataset Size and Local Updates in Heterogeneous Mobile Edge Learningcited by 2
Built on by
Not cited yet.