Skip to main navigation Skip to search Skip to main content

Stable Network Morphism

  • SUNY Buffalo
  • ByteDance Ltd.

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

Deep neural networks perform better when they are deeper. Network morphism is one of the paradigms to construct deeper neural networks. It makes developing deeper neural networks building on existing ones possible by morphing a well-trained neural network into a new one with the network function completely preserved. The morphed network also has the potential to continue growing into a more powerful one as it has more parameters. Existing network morphism schemes include Net2Net and NetMorph. However, both of them suffer from significant initial performance drop when the morphed network is continually trained. Such unstability is very much undesired for a continual learning system. In this research, we first identify the reason for the unstability, which is due to the large amount of zeros padded into the parameters. Based on this observation, we propose an algorithm based on modified gradient descent to decompose the network morphism equation. As a result, the morphed parameters are all non-zeros and the continual training process become stable. Experimental results on benchmark datasets demonstrate the effectiveness of the proposed stable network morphism scheme.

Original languageEnglish
Title of host publication2019 International Joint Conference on Neural Networks, IJCNN 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728119854
DOIs
StatePublished - Jul 2019
Event2019 International Joint Conference on Neural Networks, IJCNN 2019 - Budapest, Hungary
Duration: Jul 14 2019Jul 19 2019

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2019-July

Conference

Conference2019 International Joint Conference on Neural Networks, IJCNN 2019
Country/TerritoryHungary
CityBudapest
Period07/14/1907/19/19

Keywords

  • Deep Neural Networks
  • Network Morphism
  • Stability

Fingerprint

Dive into the research topics of 'Stable Network Morphism'. Together they form a unique fingerprint.

Cite this