Resource-Aware Heterogeneous Federated Learning using Neural Architecture Search

by   Sixing Yu, et al.

Federated Learning (FL) is extensively used to train AI/ML models in distributed and privacy-preserving settings. Participant edge devices in FL systems typically contain non-independent and identically distributed (Non-IID) private data and unevenly distributed computational resources. Preserving user data privacy while optimizing AI/ML models in a heterogeneous federated network requires us to address data heterogeneity and system/resource heterogeneity. Hence, we propose Resource-aware Federated Learning (RaFL) to address these challenges. RaFL allocates resource-aware models to edge devices using Neural Architecture Search (NAS) and allows heterogeneous model architecture deployment by knowledge extraction and fusion. Integrating NAS into FL enables on-demand customized model deployment for resource-diverse edge devices. Furthermore, we propose a multi-model architecture fusion scheme allowing the aggregation of the distributed learning results. Results demonstrate RaFL's superior resource efficiency compared to SoTA.


page 1

page 2

page 3

page 4


FedorAS: Federated Architecture Search under system heterogeneity

Federated learning (FL) has recently gained considerable attention due t...

Divide-and-Conquer the NAS puzzle in Resource Constrained Federated Learning Systems

Federated Learning (FL) is a privacy-preserving distributed machine lear...

FL-AGCNS: Federated Learning Framework for Automatic Graph Convolutional Network Search

Recently, some Neural Architecture Search (NAS) techniques are proposed ...

Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search

Neural networks often encounter various stringent resource constraints w...

Direct Federated Neural Architecture Search

Neural Architecture Search (NAS) is a collection of methods to craft the...

ELFISH: Resource-Aware Federated Learning on Heterogeneous Edge Devices

In this work, we propose ELFISH - a resource-aware federated learning fr...

Real-time Federated Evolutionary Neural Architecture Search

Federated learning is a distributed machine learning approach to privacy...

Please sign up or login with your details

Forgot password? Click here to reset