DaringFed: A Dynamic Bayesian Persuasion Pricing for Online Federated Learning under Two-sided Incomplete Information

2025/05/09 by Yun Xin, Jianfeng Lu, Xin, Yun +9
Computer Science · Social Sciences · #Computer Science and Game Theory (cs.GT) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Mobile Crowdsensing and Crowdsourcing #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2505.05842

openalex publication_date 2025/05/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Online Federated Learning (OFL) is a real-time learning paradigm that sequentially executes parameter aggregation immediately for each random arriving client. To motivate clients to participate in OFL, it is crucial to offer appropriate incentives to offset the training resource consumption. However, the design of incentive mechanisms in OFL is constrained by the dynamic variability of Two-sided Incomplete Information (TII) concerning resources, where the server is unaware of the clients' dynamically changing computational resources, while clients lack knowledge of the real-time communication resources allocated by the server. To incentivize clients to participate in training by offering dynamic rewards to each arriving client, we design a novel Dynamic Bayesian persuasion pricing for online Federated learning (DaringFed) under TII. Specifically, we begin by formulating the interaction between the server and clients as a dynamic signaling and pricing allocation problem within a Bayesian persuasion game, and then demonstrate the existence of a unique Bayesian persuasion Nash equilibrium. By deriving the optimal design of DaringFed under one-sided incomplete information, we further analyze the approximate optimal design of DaringFed with a specific bound under TII. Finally, extensive evaluation conducted on real datasets demonstrate that DaringFed optimizes accuracy and converges speed by 16.99%, while experiments with synthetic datasets validate the convergence of estimate unknown values and the effectiveness of DaringFed in improving the server's utility by up to 12.6%.

Citations

• Bayesian Persuasion
• Truthful Incentive Mechanism for Federated Learning with Crowdsourced Data Labeling
• Enhancing Federated Learning with spectrum allocation optimization and device selection
• Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspective
• Incentive Mechanism Design for Joint Resource Allocation in Blockchain-based Federated Learning
• Incentive Mechanism Design for Joint Resource Allocation in Blockchain-Based Federated Learning
• LoMar: A Local Defense Against Poisoning Attack on Federated Learning
• Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approach
• Asynchronous Federated Optimization
• LEAF: A Benchmark for Federated Settings
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Выпуклая оптимизация
• Dynamic Pricing and Advertising with Demand Learning

Related

• Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation
• Federated Learning as a Network Effects Game
• A Potential Game Perspective in Federated Learning
• A Bayesian Incentive Mechanism for Poison-Resilient Federated Learning
• Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners