Idempotent Weighted Aggregation Based on Binary Aggregation Trees
Sign Up to like & getrecommendations! Published in 2017 at "International Journal of Intelligent Systems"
DOI: 10.1002/int.21828
Abstract: We propose weighted aggregation algorithms for creating general idempotent weighted aggregators of n variables derived from related symmetric idempotent aggregators of two variables. This computational method, together with interpolative aggregation, can be used for the… read more here.
Keywords: aggregation; aggregation based; weighted aggregation; idempotent weighted ... See more keywords
Communication-Efficient Federated Deep Learning With Layerwise Asynchronous Model Update and Temporally Weighted Aggregation
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Transactions on Neural Networks and Learning Systems"
DOI: 10.1109/tnnls.2019.2953131
Abstract: Federated learning obtains a central model on the server by aggregating models trained locally on clients. As a result, federated learning does not require clients to upload their data to the server, thereby preserving the… read more here.
Keywords: communication; temporally weighted; model; learning ... See more keywords