IP-FL: Incentivized and Personalized Federated Learning
This work addresses the problem of enhancing client engagement and model performance in Federated Learning for applications with data heterogeneity and privacy constraints, representing a novel integration of incentives and personalization.
The paper tackles the interrelated challenges of incentivization and personalization in Federated Learning by proposing a mechanism that involves clients directly in clustering to improve accuracy and appeal, resulting in significant improvements such as 8-45% higher test accuracy, 3-38% better personalized model appeal, and 31-100% increased participation rates over existing models.
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.