Controlling Participation in Federated Learning with Feedback
Not on the map. Why?
Abstract (arXiv)
We address the problem of client participation in federated learning, where traditional methods typically rely on a random selection of a small subset of clients for each training round. In contrast, we propose FedBack, a deterministic approach that leverages control-theoretic principles to manage client participation in ADMM-based federated learning. FedBack models client participation as a discrete-time dynamical system and employs an integral feedback controller to adjust each client's participation rate individually, based on the client's optimization dynamics. We provide global convergence guarantees for our approach by building on the recent federated learning research. Numerical experiments on federated image classification demonstrate that FedBack achieves up to 50% improvement in communication and computational efficiency over algorithms that rely on a random selection of clients.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 34 references that are in the map. First posted on arXiv 28 Nov 2024.
Builds on
25 of 34 references.
References · 25
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
- 2021Model-Contrastive Federated Learningcited by 766
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
- 2020Federated Learning with Matched Averagingcited by 564
- 2021Federated Learning Based on Dynamic Regularizationcited by 562
- 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
- 2020FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Datacited by 144
- 2016A Variational Perspective on Accelerated Methods in Optimizationcited by 110
- 2014Analysis and Design of Optimization Algorithms via Integral Quadratic Constraintscited by 105
13 more
- 2018LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learningcited by 96
- 2022Federated Learning via Inexact ADMMcited by 44
- 2022FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participationcited by 36
- 2021FedDR -- Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimizationcited by 29
- 2022FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneitycited by 25
- 2015A General Analysis of the Convergence of ADMMcited by 22
- 2022Decentralized Event-Triggered Federated Learning with Heterogeneous Communication Thresholdscited by 9
- 2020Continuous-time Lower Bounds for Gradient-based Algorithmscited by 7
- 2024Towards a Systems Theory of Algorithmscited by 7
- 2023Online Learning under Adversarial Nonlinear Constraintscited by 6
- 2023A Dynamical Systems Perspective on Discrete Optimizationcited by 3
- 2024Distributed Event-Based Learning via ADMMcited by 3
- 2017Distributed Event-Based State Estimation for Networked Systems: An LMI-Approachcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.