Deep Model Compression and Inference Speedup of Sum-Product Networks on Tensor Trains

Ching Yun Ko, Cong Chen, Zhuolun He, Yuke Zhang, Kim Batselier, Ngai Wong

Research output: Contribution to journalArticleScientificpeer-review

2 Citations (Scopus)
7 Downloads (Pure)

Abstract

Sum-product networks (SPNs) constitute an emerging class of neural networks with clear probabilistic semantics and superior inference speed over other graphical models. This brief reveals an important connection between SPNs and tensor trains (TTs), leading to a new canonical form which we call tensor SPNs (tSPNs). Specifically, we demonstrate the intimate relationship between a valid SPN and a TT. For the first time, through mapping an SPN onto a tSPN and employing specially customized optimization techniques, we demonstrate improvements up to a factor of 100 on both model compression and inference speedup for various data sets with negligible loss in accuracy.

Original languageEnglish
Pages (from-to)2665-2671
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume31
Issue number7
DOIs
Publication statusPublished - 2020

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care

Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

  • Model compression
  • sum-product network (SP)
  • tensor train (TT)

Fingerprint

Dive into the research topics of 'Deep Model Compression and Inference Speedup of Sum-Product Networks on Tensor Trains'. Together they form a unique fingerprint.

Cite this