[edit]
Probabilistic Fusion of Neural Networks that Incorporates Global Information
Proceedings of The 14th Asian Conference on Machine
Learning, PMLR 189:1149-1164, 2023.
Abstract
As one of the approaches in Federated Learning,
model fusion distills models trained on local
clients into a global model. The previous method,
Probabilistic Federated Neural Matching (PFNM), can
match and fuse local neural networks with varying
global model sizes and data heterogeneity using the
Bayesian nonparametric framework. However, the
alternating optimization process applied by PFNM
causes absence of global neuron information. In this
paper, we propose a new method that extends PFNM by
introducing a Kullback-Leibler (KL) divergence
penalty, so that it can exploit information in both
local and global neurons. We show theoretically that
the extended PFNM with a penalty derived from KL
divergence can fix the drawback of PFNM by making a
balance between Euclidean distance and the prior
probability of neurons. Experiments on deep
fully-connected as well as deep convolutional neural
networks demonstrate that our new method outperforms
popular state-of-the-art federated learning methods
in both image classification and semantic
segmentation tasks.