FedECADO: A Dynamical System Model of Federated Learning
This addresses performance issues in federated learning for distributed machine learning applications, representing an incremental improvement over existing methods.
The paper tackles performance limitations in federated learning caused by heterogeneous data distributions and computational workloads by proposing FedECADO, a new algorithm based on a dynamical system model. It achieves higher classification accuracies compared to FedProx and FedNova in various heterogeneous scenarios.
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.