Exploring Amplified Heterogeneity Arising From Heavy-Tailed Distributions in Federated Learning
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Mobile Computing"
DOI: 10.1109/tmc.2024.3398052
Abstract: Federated Learning (FL) has emerged as a privacy-preserving paradigm enabling collaborative model training among distributed clients. However, current FL methods operate under the closed-world assumption, i.e., all local training data originates from a global labeled… read more here.
Keywords: exploring amplified; heavy tailed; federated learning; aggregation ... See more keywords