Jiahao Gan

MoFedAGR: Mitigating client drift with adaptive gradient regularization and global momentum in federated learning.

This work comprehensively considering the effects of client drift during the training process, and quantifying it as the aggregation error, proposes adaptive gradient regularization, which is based on gradient regularization and further and applies different regularization strengths to each parameter based on the magnitude of the parameter variance between the local model and the global model.