FedMix: Approximation of Mixup under Mean Augmented Federated Learning
This addresses the problem of data heterogeneity for federated learning systems, offering an incremental improvement over existing methods.
The paper tackles performance degradation in federated learning due to data heterogeneity by proposing FedMix, a data augmentation method under the Mean Augmented Federated Learning framework, which shows greatly improved performance on standard benchmark datasets under highly non-iid settings.
Federated learning (FL) allows edge devices to collectively learn a model without directly sharing data within each device, thus preserving privacy and eliminating the need to store data globally. While there are promising results under the assumption of independent and identically distributed (iid) local data, current state-of-the-art algorithms suffer from performance degradation as the heterogeneity of local data across clients increases. To resolve this issue, we propose a simple framework, Mean Augmented Federated Learning (MAFL), where clients send and receive averaged local data, subject to the privacy requirements of target applications. Under our framework, we propose a new augmentation algorithm, named FedMix, which is inspired by a phenomenal yet simple data augmentation method, Mixup, but does not require local raw data to be directly shared among devices. Our method shows greatly improved performance in the standard benchmark datasets of FL, under highly non-iid federated settings, compared to conventional algorithms.