Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets
This addresses bias in synthetic data generation for federated learning, which is incremental as it builds on FedGAN to mitigate a specific issue.
The paper tackled the problem of biased data generation in Federated GANs under non-iid settings by proposing Bias-Free FedGAN, which generates metadata at the aggregator to retrain the model, achieving bias-free synthetic datasets with the same communication cost as FedGAN, as validated on MNIST and FashionMNIST datasets.
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.