Federated Averaging
Federated Averaging (FedAvg) is a machine learning technique enabling collaborative model training across decentralized devices without directly sharing sensitive data. Current research focuses on addressing challenges like data heterogeneity (variations in data distributions across devices) and communication efficiency, often employing techniques such as variance reduction, adaptive learning rates, and novel aggregation methods beyond simple averaging, including generative approaches and model recombination. These advancements aim to improve the accuracy and scalability of FedAvg for diverse applications, particularly in privacy-sensitive domains like healthcare and mobile computing, where data decentralization is crucial.
Papers
December 2, 2024
November 27, 2024
November 10, 2024
November 2, 2024
October 4, 2024
October 2, 2024
September 11, 2024
September 9, 2024
September 8, 2024
August 27, 2024
July 17, 2024
July 16, 2024
June 18, 2024
June 12, 2024
May 31, 2024
May 4, 2024
April 24, 2024
February 19, 2024
February 17, 2024