Using adversarial images to improve outcomes of federated learning for non-IID data
This addresses data imbalance issues in federated learning for applications like image classification, but it is incremental as it builds on existing methods like Weighted Federated Averaging.
The paper tackled the problem of unbalanced, non-IID data in federated learning by using adversarial images to guide training, resulting in improved performance on MNIST and CIFAR-10 datasets.
One of the important problems in federated learning is how to deal with unbalanced data. This contribution introduces a novel technique designed to deal with label skewed non-IID data, using adversarial inputs, created by the I-FGSM method. Adversarial inputs guide the training process and allow the Weighted Federated Averaging to give more importance to clients with 'selected' local label distributions. Experimental results, gathered from image classification tasks, for MNIST and CIFAR-10 datasets, are reported and analyzed.