RealFM: A Realistic Mechanism to Incentivize Data Contribution and Device Participation

Published: 28 Oct 2023, Last Modified: 21 Nov 2023FL@FM-NeurIPS’23 PosterEveryoneRevisionsBibTeX
Student Author Indication: Yes
Keywords: Federated Learning, Realistic, Mechanisms, Utility
TL;DR: We propose a truly federated learning mechanism which realistically models device utility and incentivizes data contribution and device participation within federated training all while provably removing the free-rider phenomena.
Abstract: Edge device participation in federating learning (FL) has been typically studied under the lens of device-server communication (e.g., device dropout) and assumes an undying desire from edge devices to participate in FL. As a result, current FL frameworks are flawed when implemented in real-world settings, with many encountering the free-rider problem. In a step to push FL towards realistic settings, we propose RealFM: the first truly federated mechanism which (1) realistically models device utility, (2) incentivizes data contribution and device participation, and (3) provably removes the free-rider phenomena. RealFM does not require data sharing and allows for a non-linear relationship between model accuracy and utility, which improves the utility gained by the server and participating devices compared to non-participating devices as well as devices participating in other FL mechanisms. On real-world data, RealFM improves device and server utility, as well as data contribution, by up to 3 magnitudes and $7$x respectively compared to baseline mechanisms.
Submission Number: 7