CARE: Compatibility-Aware Incentive Mechanisms for Federated Learning with Budgeted Requesters

2025-04-22

AI Summary

This paper addresses two key challenges in budget-constrained requester-driven worker recruitment for federated learning: (i) reduced efficiency due to inter-worker communication and data-source incompatibility, and (ii) limited scalability imposed by tight requester budgets. We propose the first incentive mechanism framework jointly modeling worker compatibility and private costs. We design two mechanisms—CARE-CO (collaborative) and CARE-NO (non-collaborative)—both rigorously satisfying truthfulness, individual rationality, budget feasibility, and approximation optimality. Leveraging tools from game theory, mechanism design, and approximation algorithms, our theoretical analysis is complemented by empirical evaluation. Experiments demonstrate that, compared to state-of-the-art baselines, our approach reduces communication overhead by 18.7%, improves task completion rate by 23.4%, and significantly accelerates model convergence while enhancing generalization performance.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Multiagent Systems: Mechanism Design
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Federated learning (FL) is a promising approach that allows requesters (eg, servers) to obtain local training models from workers (e.g., clients). Since workers are typically unwilling to provide training services/models freely and voluntarily, many incentive mechanisms in FL are designed to incentivize participation by offering monetary rewards from requesters. However, existing studies neglect two crucial aspects of real-world FL scenarios. First, workers can possess inherent incompatibility characteristics (e.g., communication channels and data sources), which can lead to degradation of FL efficiency (e.g., low communication efficiency and poor model generalization). Second, the requesters are budgeted, which limits the amount of workers they can hire for their tasks. In this paper, we investigate the scenario in FL where multiple budgeted requesters seek training services from incompatible workers with private training costs. We consider two settings: the cooperative budget setting where requesters cooperate to pool their budgets to improve their overall utility and the non-cooperative budget setting where each requester optimizes their utility within their own budgets. To address efficiency degradation caused by worker incompatibility, we develop novel compatibility-aware incentive mechanisms, CARE-CO and CARE-NO, for both settings to elicit true private costs and determine workers to hire for requesters and their rewards while satisfying requester budget constraints. Our mechanisms guarantee individual rationality, truthfulness, budget feasibility, and approximation performance. We conduct extensive experiments using real-world datasets to show that the proposed mechanisms significantly outperform existing baselines.

Problem

• Address worker incompatibility in federated learning efficiency
• Manage budget constraints for multiple FL requesters
• Design incentive mechanisms for truthful cost reporting

Innovation

• Compatibility-aware incentive mechanisms for FL
• Handles budgeted requesters and incompatible workers
• Ensures truthfulness and budget feasibility