IP-FL: Incentivized and Personalized Federated Learning

TL;DR

This paper introduces IP-FL, a federated learning framework that combines incentivization and personalization by involving clients directly in cluster identification, leading to improved accuracy, engagement, and model appeal.

Contribution

It proposes a novel incentive mechanism that integrates personalization and client involvement, overcoming privacy limitations in clustering for federated learning.

Findings

Test accuracy improved by 8-45%.

Participation rates increased by 31-100%.

Personalized model appeal enhanced by 3-38%.

Abstract

Existing incentive solutions for traditional Federated Learning (FL) focus on individual contributions to a single global objective, neglecting the nuances of clustered personalization with multiple cluster-level models and the non-monetary incentives such as personalized model appeal for clients. In this paper, we first propose to treat incentivization and personalization as interrelated challenges and solve them with an incentive mechanism that fosters personalized learning. Additionally, current methods depend on an aggregator for client clustering, which is limited by a lack of access to clients' confidential information due to privacy constraints, leading to inaccurate clustering. To overcome this, we propose direct client involvement, allowing clients to indicate their cluster membership preferences based on data distribution and incentive-driven feedback. Our approach enhances the personalized model appeal for self-aware clients with high-quality data leading to their active and consistent participation. Our evaluation demonstrates significant improvements in test accuracy (8-45%), personalized model appeal (3-38%), and participation rates (31-100%) over existing FL models, including those addressing data heterogeneity and personalization.