Hierarchically Fair Federated Learning

Abstract

When the federated learning is adopted among competitive agents with siloed datasets, agents are self-interested and participate only if they are fairly rewarded. To encourage the application of federated learning, this paper employs a management strategy, i.e., more contributions should lead to more rewards. We propose a novel hierarchically fair federated learning (HFFL) framework. Under this framework, agents are rewarded in proportion to their pre-negotiated contribution levels. HFFL+ extends this to incorporate heterogeneous models. Theoretical analysis and empirical evaluation on several datasets confirm the efficacy of our frameworks in upholding fairness and thus facilitating federated learning in the competitive settings.

References in corpus (9)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Fair Resource Allocation in Federated Learning
• Data Shapley: Equitable Valuation of Data for Machine Learning
• Satisfying Real-world Goals with Dataset Constraints
• Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach
• Rewarding High-Quality Data via Influence Functions
• Learning Fairness in Multi-Agent Systems

Cited by in corpus (10)

• Ditto: Fair and Robust Federated Learning Through Personalization
• A Field Guide to Federated Optimization
• Towards Fairness-Aware Federated Learning
• Improving Fairness for Data Valuation in Horizontal Federated Learning
• Improving Fairness via Federated Learning
• Prototype Guided Federated Learning of Visual Feature Representations
• Is Shapley Value fair? Improving Client Selection for Mavericks in Federated Learning
• One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
• Efficient Client Contribution Evaluation for Horizontal Federated Learning
• Models of fairness in federated learning