FedSD: A New Federated Learning Structure Used in Non-iid Data
Minmin Yi (Tsinghua University); Houchun Ning (Tsinghua University); Peng Liu (PingAn Tech/Hong Kong Polytechnic University)
-
SPS
IEEE Members: $11.00
Non-members: $15.00
One of the most challenging problems in federated learning
is the convergence speed problem caused by heterogeneity.
We propose a novel structure called FedSD, a new method
to accelerate the model convergence. We change the one-
stage-cycle iteration structure to a 2-stage-cycle one to get
the latest global gradient descent direction which can guide
the model training direction. We instantiate algorithms using
FedSD to improve the performance of experiments on several
public datasets. Our empirical studies validate the excellent
performance of FedSD.