SelfFed: Self-Supervised Federated Learning for Data Heterogeneity and Label Scarcity in Medical Images
This addresses data heterogeneity and label scarcity in federated learning for medical imaging, offering incremental improvements over existing methods.
The paper tackled performance degradation in self-supervised federated learning due to data heterogeneity and label scarcity in medical images, proposing the SelfFed framework that achieved improvements of up to 8.8% and 4.1% on non-IID datasets and outperformed baselines with only 10% labeled data.
Self-supervised learning in the federated learning paradigm has been gaining a lot of interest both in industry and research due to the collaborative learning capability on unlabeled yet isolated data. However, self-supervised based federated learning strategies suffer from performance degradation due to label scarcity and diverse data distributions, i.e., data heterogeneity. In this paper, we propose the SelfFed framework for medical images to overcome data heterogeneity and label scarcity issues. The first phase of the SelfFed framework helps to overcome the data heterogeneity issue by leveraging the pre-training paradigm that performs augmentative modeling using Swin Transformer-based encoder in a decentralized manner. The label scarcity issue is addressed by fine-tuning paradigm that introduces a contrastive network and a novel aggregation strategy. We perform our experimental analysis on publicly available medical imaging datasets to show that SelfFed performs better when compared to existing baselines and works. Our method achieves a maximum improvement of 8.8% and 4.1% on Retina and COVID-FL datasets on non-IID datasets. Further, our proposed method outperforms existing baselines even when trained on a few (10%) labeled instances.