IEEE

FedDiffRec: A Module-wise Training Approach for Diffusion-Based Recommendation in Federated Learning

Abstract: Federated Learning (FL) has become a prominent framework for maintaining privacy in recommender systems by enabling decentralized model training. Despite its benefits, traditional Federated ...
IEEE

Unbalanced Magnetic Radial Pull During Module Open Circuit Fault in a Multi-Modular, High Voltage PM Synchronous Direct Drive Generator for Offshore Wind

Abstract: This paper compares an analytic and finite element method (FEM) for calculating unbalanced magnetic pull in a multi-modular PM synchronous generator with tangential air gaps between the ...