Scalable and Portable Federated Learning Simulation Engine

Résumé fourni par la source

Federated learning (FL) is one of the most promising approaches to ensure privacy in the application of data-driven techniques to sensitive information. However, the implementation of such approaches in a production environment is still an important challenge. In this paper, we present a scalable, portable, hardware-independent, model-agnostic FL Simulation Engine (FLSE) with the aim of easing the job of researchers who want to train FL models to be deployed in production environments. The FLSE offers a tool that can be used both standalone or embedded within a larger architecture, it can be deployed seamlessly and allows concurrent, scalable, and highly available V&V assessment support for FL models. The tool allows researchers to understand the behaviour, in terms of metric performance, of their proposed models in production scenarios, allowing a boost in trustworthiness towards ethical AI.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.