SatDL: Jointly Optimizing Data Redistribution and Training for Satellite-Based Distributed Learning
SatDL is presented, a data-redistribution framework designed to minimize total end-to-end learning time and onboard energy consumption in satellite-based distributed learning, and develops a Distributor-Critic framework that jointly models and optimizes data-transfer delay and training time.
Hao Wu, Kin Whye Chew, Yi-Zhan Han et al.
· 0 citations