FedECADO: A Dynamical System Model of Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning harnesses the power of distributed optimization to train a unified machine learning model across separate clients. However, heterogeneous data distributions and computational workloads can lead to inconsistent updates and limit model performance. This work tackles these challenges by proposing FedECADO, a new algorithm inspired by a dynamical system representation of the federated learning process. FedECADO addresses non-IID data distribution through an aggregate sensitivity model that reflects the amount of data processed by each client. To tackle heterogeneous computing, we design a multi-rate integration method with adaptive step-size selections that synchronizes active client updates in continuous time. Compared to prominent techniques, including FedProx and FedNova, FedECADO achieves higher classification accuracies in numerous heterogeneous scenarios.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 13 Oct 2024.
Builds on
18 of 26 references.
References · 18
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
- 2019Advances and Open Problems in Federated Learningcited by 3,040
- 2018Federated Optimization in Heterogeneous Networkscited by 2,981
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,227
- 2020Adaptive Federated Optimizationcited by 1,041
- 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 903
- 2021Federated Learning Based on Dynamic Regularizationcited by 559
- 2021Federated Learning on Non-IID Data: A Surveycited by 346
- 2021A Field Guide to Federated Optimizationcited by 314
- 2020FedSplit: An algorithmic framework for fast federated optimizationcited by 108
- 2020FedDANE: A Federated Newton-Type Methodcited by 76
6 more
- 2023FedExP: Speeding Up Federated Averaging via Extrapolationcited by 69
- 2020Faster Non-Convex Federated Learning via Global and Local Momentumcited by 48
- 2020On the Outsized Importance of Learning Rates in Local Update Methodscited by 36
- 2022Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimizationcited by 23
- 2021Coordinating Momenta for Cross-silo Federated Learningcited by 9
- 2023An Equivalent Circuit Approach to Distributed Optimizationcited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.