FedECADO: A Dynamical System Model of Federated Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Distributed OptimizationFederated LearningmodelSensitivitySimilar Papers 제목 키워드 기반
FedSysID: A Federated Approach to Sample-Efficient System Identification
We study the problem of learning a linear system model from the observations of $M$ clients. The catch: Each client is observing data from a different dynamical system. This work addresses the question of how multiple cl…
Federated LearningAdaptive Federated Learning via Dynamical System Model
Hyperparameter selection is critical for stable and efficient convergence of heterogeneous federated learning, where clients differ in computational capabilities, and data distributions are non-IID. Tuning hyperparameter…
Federated LearningDecentralized digital twins of complex dynamical systems
In this paper, we introduce a decentralized digital twin (DDT) framework for dynamical systems and discuss the prospects of the DDT modeling paradigm in computational science and engineering applications. The DDT approac…
BIG-bench Machine LearningFederated LearningFederated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints
Federated learning systems facilitate training of global models in settings where potentially heterogeneous data is distributed across a large number of clients. Such systems operate in settings with intermittent client …
BenchmarkingFederated LearningControlling Participation in Federated Learning with Feedback
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, …
Computational EfficiencyFederated Learningimage-classificationImage Classification