Non-IID Federated Learning With Sharper Risk Bound.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3213187
Abstract: In federated learning (FL), the not independently or identically distributed (non-IID) data partitioning impairs the performance of the global model, which is a severe problem to be solved. Despite the extensive literature related to the… read more here.
Keywords: local rademacher; non iid; federated learning; risk ... See more keywords