Bayesian Federated Neural Matching That Completes Full Information
Abstract
Federated learning is a contemporary machine learning paradigm where locally trained models are distilled into a global model. Due to the intrinsic permutation invariance of neural networks, Probabilistic Federated Neural Matching (PFNM) employs a Bayesian nonparametric framework in the generation process of local neurons, and then creates a linear sum assignment formulation in each alternative optimization iteration. But according to our theoretical analysis, the optimization iteration in PFNM omits global information from existing. In this study, we propose a novel approach that overcomes this flaw by introducing a Kullback-Leibler divergence penalty at each iteration. The effectiveness of our approach is demonstrated by experiments on both image classification and semantic segmentation tasks.
BibTeX
@article{Xiao_Cheng_2023, title={Bayesian Federated Neural Matching That Completes Full Information}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26245}, DOI={10.1609/aaai.v37i9.26245}, abstractNote={Federated learning is a contemporary machine learning paradigm where locally trained models are distilled into a global model. Due to the intrinsic permutation invariance of neural networks, Probabilistic Federated Neural Matching (PFNM) employs a Bayesian nonparametric framework in the generation process of local neurons, and then creates a linear sum assignment formulation in each alternative optimization iteration. But according to our theoretical analysis, the optimization iteration in PFNM omits global information from existing. In this study, we propose a novel approach that overcomes this flaw by introducing a Kullback-Leibler divergence penalty at each iteration.
The effectiveness of our approach is demonstrated by experiments on both image classification and semantic segmentation tasks.}, number={9}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Xiao, Peng and Cheng, Samuel}, year={2023}, month={Jun.}, pages={10473-10480} }