A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning

Abstract

Federated learning (FL) is an emerging practical framework for effective and scalable machine learning among multiple participants, such as end users, organizations and companies. However, most existing FL or distributed learning frameworks have not well addressed two important issues together: collaborative fairness and adversarial robustness (e.g. free-riders and malicious participants). In conventional FL, all participants receive the global model (equal rewards), which might be unfair to the high-contributing participants. Furthermore, due to the lack of a safeguard mechanism, free-riders or malicious adversaries could game the system to access the global model for free or to sabotage it. In this paper, we propose a novel Robust and Fair Federated Learning (RFFL) framework to achieve collaborative fairness and adversarial robustness simultaneously via a reputation mechanism. RFFL maintains a reputation for each participant by examining their contributions via their uploaded gradients (using vector similarity) and thus identifies non-contributing or malicious participants to be removed. Our approach differentiates itself by not requiring any auxiliary/validation dataset. Extensive experiments on benchmark datasets show that RFFL can achieve high fairness and is very robust to different types of adversaries while achieving competitive predictive accuracy.

arXiv commentAccepted as Oral presentation at International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2021 (FL-ICML'21)

References in corpus (14)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• On the difficulty of training Recurrent Neural Networks
• Convolutional Neural Networks for Sentence Classification
• Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
• Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
• Mitigating Sybils in Federated Learning Poisoning
• Agnostic Federated Learning
• Threats to Federated Learning: A Survey
• Local SGD Converges Fast and Communicates Little
• signSGD with Majority Vote is Communication Efficient And Fault Tolerant
• Federated Model Distillation with Noise-Free Differential Privacy
• Differentially Private Fair Learning
• Rewarding High-Quality Data via Influence Functions
• ByGARS: Byzantine SGD with Arbitrary Number of Attackers

Cited by in corpus (5)

• Ditto: Fair and Robust Federated Learning Through Personalization
• Towards Fairness-Aware Federated Learning
• Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources
• Federated Learning with Fair Averaging
• Secure Distributed Training at Scale