Structured Bayesian Compression for Deep Models in Mobile-Enabled Devices for Connected Healthcare

Sijia Chen, Bin Song, Xiaojiang Du, Nadra Guizani

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Deep models, typically deep neural networks, have millions of parameters, analyze medical data accurately, yet in a time-consuming method. However, energy cost effectiveness and computational efficiency are important for prerequisites developing and deploying mobile-enabled devices, the mainstream trend in connected healthcare. Therefore, deep models' compression has become a problem of great significance for real-time health services. In this article, we first emphasize the use of Bayesian learning for model sparsity, effectively reducing the number of parameters while maintaining model performance. Specifically, with sparsity inducing priors, large parts of the network can be pruned with a simple retraining of arbitrary datasets. Then, we propose a novel structured Bayesian compression architecture by adaptively learning both group sparse and block sparse while also designing sparse-oriented mixture priors to improve the expandability of the compression model. Experimental results from both simulated datasets (MNIST) as well as practical medical datasets (Histopathologic Cancer) demonstrate the effectiveness and good performance of our framework on deep model compression.

Original languageEnglish
Article number8823872
Pages (from-to)142-149
Number of pages8
JournalIEEE Network
Volume34
Issue number2
DOIs
StatePublished - 1 Mar 2020

Fingerprint

Dive into the research topics of 'Structured Bayesian Compression for Deep Models in Mobile-Enabled Devices for Connected Healthcare'. Together they form a unique fingerprint.

Cite this