Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets

Abstract

Federated Generative Adversarial Network (FedGAN) is a communication-efficient approach to train a GAN across distributed clients without clients having to share their sensitive training data. In this paper, we experimentally show that FedGAN generates biased data points under non-independent-and-identically-distributed (non-iid) settings. Also, we propose Bias-Free FedGAN, an approach to generate bias-free synthetic datasets using FedGAN. Our approach generates metadata at the aggregator using the models received from clients and retrains the federated model to achieve bias-free results for image synthesis. Bias-Free FedGAN has the same communication cost as that of FedGAN. Experimental results on image datasets (MNIST and FashionMNIST) validate our claims.

References in corpus (9)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• DeepFakes: a New Threat to Face Recognition? Assessment and Detection
• Generative Moment Matching Networks
• Mitigating Bias in Federated Learning
• Fairness and Accuracy in Federated Learning
• FedGAN: Federated Generative Adversarial Networks for Distributed Data
• Improving the Fairness of Deep Generative Models without Retraining
• FairFaceGAN: Fairness-aware Facial Image-to-Image Translation
• DPD-InfoGAN: Differentially Private Distributed InfoGAN

Cited by in corpus (1)

• FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learning