Improving Local Training in Federated Learning via Temperature Scaling
This addresses data heterogeneity issues for federated learning systems, offering incremental improvements.
The paper tackled the problem of data heterogeneity in federated learning by proposing a novel training approach, resulting in up to 6X faster convergence and 3.37% higher inference accuracy.
Federated learning is inherently hampered by data heterogeneity: non-i.i.d. training data over local clients. We propose a novel model training approach for federated learning, FLex&Chill, which exploits the Logit Chilling method. Through extensive evaluations, we demonstrate that, in the presence of non-i.i.d. data characteristics inherent in federated learning systems, this approach can expedite model convergence and improve inference accuracy. Quantitatively, from our experiments, we observe up to 6X improvement in the global federated learning model convergence time, and up to 3.37% improvement in inference accuracy.