Susanna Peretti

FedAvg for HAR: Exploring the Tradeoff Between Personalized and Generalization Accuracy

Experimental results of the FedAvg algorithm applied to the Human Activity Recognition domain show that, although FedAvg confirms a higher degree of personalization capabilities while keeping a high degree of generalization with respect to the traditional centralized learning, this result is not so obvious under stressful conditions, such as when varying class distribution over clients.