IEEE

Federated Learning for Distribution Skewed Data Using Sample Weights

Abstract: One of the most challenging issues in federated learning (FL) is that the data are often not independent and identically distributed (non-IID). Clients are expected to contribute the same ...
IEEE

A Fusing Domain Feature and Sharing Label Space-Based Fault Diagnosis Approach for Different Distribution and Unlabeled Rolling Bearing Sample

Abstract: As the different distributions between the source and target domains, rolling bearing fault diagnosis based on domain adaptation (DA) has achieved a good result in unlabeled sample fault ...