Additive Angular Margin Loss for Federated Learning in Image Classification

Federated learning (FL) is a method that leverages data from multiple sources to enhance deep learning models while safeguarding data privacy. This approach finds applications in diverse domains such as healthcare, entertainment, and user experience enhancement. Despite its effectiveness, FL’s performance is still low compared to centralized training methods, necessitating further improvements. Particularly in critical areas such as medicine, where accurate model predictions are crucial, conventional FL algorithms fall short compared to centralized training. This study introduces a new training approach to further improve the vanilla FL algorithm. Our proposed method takes advantage of feature-based adjustments using cosine angles by incorporating an angular margin loss function alongside the cross-entropy loss. It notably enhances the accuracy of the aggregated models on datasets such as MNIST, CIFAR10, and CIFAR100 while maintaining FL’s privacy-preserving attributes. Moreover, we conduct a comprehensive comparative analysis of the proposed method against existing FL algorithms to evaluate the impact of the angular margin loss function on the learning process. Our experimental results underscore the effectiveness of the proposed algorithm when compared with standard benchmarks, proving its potential to advance the field of FL.