Work

Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints

Year: 2022

Type: article

Abstract: Federated learning systems facilitate the training of global models across large numbers of distributed edge-devices with potentially heterogeneous data. Such systems operate in resource constrained settings with intermittent client availability and/or time-varying communication constraints. As a result, the global models trained by federated learning systems may be biased towards clients with higher availability. We proposeFederatedAveragingAided by anAdaptiveSamplingTechnique (F3ast), an unbiased algorithm that dynamically learns an availability-dependent client selection strategy which asymptotically minimizes the impact of client-sampling variance on the global model's convergence, enhancing performance of federated learning. The proposed algorithm is tested in a variety of settings for intermittently available clients operating under communication constraints, and its efficacy demonstrated on synthetic data and realistically federated benchmarking experiments using CIFAR100 and Shakespeare datasets. We report up to 186% and 8% accuracy improvements overFedAvg, and 8% and 7% overFedAdamon CIFAR100 and Shakespeare, respectively.

Source: IEEE Journal of Selected Topics in Signal Processing

DOI: 10.1109/jstsp.2022.3224590

Authors: Monica Ribero, Haris Vikalo, Gustavo de Veciana

Institution: The University of Texas at Austin

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, National Institute of Standards and Technology

Award: RINGS: Scalable and Resilient Networked Learning Systems