Search Results for author:
Found 2 papers, 1 papers with code
FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropout
Building on this dropout technique, we develop an adaptive training framework, Federated Learning using Invariant Dropout (FLuID).
Reducing Impacts of System Heterogeneity in Federated Learning using Weight Update Magnitudes
Invariant Dropout uses neuron updates from the non-straggler clients to develop a tailored sub-models for each straggler during each training iteration.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
