Policy-Based Federated Learning
Kleomenis Katevas
Eugene Bagdasaryan
J. Waterman
Mohamad Mounir Safadieh
Eleanor Birrell
Hamed Haddadi
D. Estrin

Abstract
In this paper we present PoliFL, a decentralized, edge-based framework that supports heterogeneous privacy policies for federated learning. We evaluate our system on three use cases that train models with sensitive user data collected by mobile phones - predictive text, image classification, and notification engagement prediction - on a Raspberry Pi edge device. We find that PoliFL is able to perform accurate model training and inference within reasonable resource and time budgets while also enforcing heterogeneous privacy policies.
View on arXivComments on this paper