Right Reward Right Time for Federated Learning
Thanh Linh Nguyen, Dinh Thai Hoang, Diep N. Nguyen, Quoc-Viet Pham
TL;DR
This work tackles the challenge of CLPs in federated learning by introducing R3T, a time-aware incentive mechanism that uses contract theory and blockchain to elicit early, high-quality client contributions. The cloud designs a menu of contracts that align incentives with clients' time and system capabilities, deriving optimal strategies under complete and incomplete information and ensuring IR and IC constraints. The approach yields substantial improvements in convergence speed and cloud utility, achieving up to a 300% faster convergence and up to a 47.6% reduction in participating clients compared with benchmarks, while maintaining competitive model accuracy. By integrating smart contracts and CLP-aware incentives, R3T offers a transparent, fair, and auditable framework for incentive design in privacy-preserving FL with information asymmetry and critical learning periods.
Abstract
Critical learning periods (CLPs) in federated learning (FL) refer to early stages during which low-quality contributions (e.g., sparse training data availability) can permanently impair the learning performance of the global model owned by the model owner (i.e., the cloud server). However, strategies to motivate clients with high-quality contributions to join the FL training process and share trained model updates during CLPs remain underexplored. Additionally, existing incentive mechanisms in FL treat all training periods equally, which consequently fails to motivate clients to participate early. Compounding this challenge is the cloud's limited knowledge of client training capabilities due to privacy regulations, leading to information asymmetry. Therefore, in this article, we propose a time-aware incentive mechanism, called Right Reward Right Time (R3T), to encourage client involvement, especially during CLPs, to maximize the utility of the cloud in FL. Specifically, the cloud utility function captures the trade-off between the achieved model performance and payments allocated for clients' contributions, while accounting for clients' time and system capabilities, efforts, joining time, and rewards. Then, we analytically derive the optimal contract for the cloud and devise a CLP-aware mechanism to incentivize early participation and efforts while maximizing cloud utility, even under information asymmetry. By providing the right reward at the right time, our approach can attract the highest-quality contributions during CLPs. Simulation and proof-of-concept studies show that R3T increases cloud utility and is more economically effective than benchmarks. Notably, our proof-of-concept results show up to a 47.6% reduction in the total number of clients and up to a 300% improvement in convergence time while reaching competitive test accuracies compared with incentive mechanism benchmarks.