ICT Express · 2023 · 20 citations · 13 references
ComputingComputer ScienceComputer VisionHeterogeneous ComputingMachine LearningDeep LearningFederated LearningMachine Learning For Big DataRepresentation LearningScalable Machine LearningAccuracyCommon InformationCommunication Overhead ReductionCross-device Federated LearningFederated Training ArchitectureHeterogeneous Model IntegrationTraining
In this paper, we propose a novel federated learning framework named FedHM that aims to address the challenge of training models on heterogeneous devices with varying architectures. Our approach enables the collaborative training of diverse local models by sharing a fully convolutional network (FCN) architecture that effectively extracts the local-to-global representations. By leveraging the weights with respect to this abstraction as common information across different DNN architectures, FedHM achieves efficient federated learning with minimal computational and communication overhead. We compare FedHM with three federated learning frameworks using two datasets for image classification tasks. Our results show that FedHM achieves high accuracy with considerably lower computational and communication costs compared to the other frameworks.
13
Three Approaches for Personalization with Applications to Federated Learning
Yishay Mansour, Mehryar Mohri, Jae Hun Ro et al. · arXiv (Cornell University) · 2020 · 322 citations · Full text