Model-Agnostic Federated Learning

TL;DR

This paper introduces MAFL, a model-agnostic federated learning framework that extends FL beyond DNNs, demonstrating its correctness, flexibility, scalability, and hardware compatibility.

Contribution

It presents the first FL system not tied to specific models, integrating AdaBoost.F with OpenFL to enable diverse machine learning approaches.

Findings

Achieved 5.5x speedup in FL training.

Validated scalability up to 64 nodes.

Ensured compatibility across multiple hardware architectures.

Abstract

Since its debut in 2016, Federated Learning (FL) has been tied to the inner workings of Deep Neural Networks (DNNs). On the one hand, this allowed its development and widespread use as DNNs proliferated. On the other hand, it neglected all those scenarios in which using DNNs is not possible or advantageous. The fact that most current FL frameworks only allow training DNNs reinforces this problem. To address the lack of FL solutions for non-DNN-based use cases, we propose MAFL (Model-Agnostic Federated Learning). MAFL marries a model-agnostic FL algorithm, AdaBoost.F, with an open industry-grade FL framework: Intel OpenFL. MAFL is the first FL system not tied to any specific type of machine learning model, allowing exploration of FL scenarios beyond DNNs and trees. We test MAFL from multiple points of view, assessing its correctness, flexibility and scaling properties up to 64 nodes. We optimised the base software achieving a 5.5x speedup on a standard FL scenario. MAFL is compatible with x86-64, ARM-v8, Power and RISC-V.