ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Towards Understanding Architectural Effects on Knowledge Distillation
Cited 0 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Ik-Hee Shin, Yong-Hyuk Moo, Yong-Ju Lee
Issue Date
2020-10
Citation
International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1144-1146
Publisher
IEEE
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/ICTC49870.2020.9289630
Abstract
Knowledge distillation is a promising model compression solution, which adopts an apprenticeship (teacher-student) learning approach. Even referring to the same teacher network, it has reported different distillation performance according to a used student network architecture in current works. To tackle this issue, we investigate how scaling depth and width over layers influences learning capability based on distillation. Our experiment results show that depth scaling is a more determinant factor than width for selecting a smaller network in knowledge distillation.
KSP Keywords
Experiment results, Knowledge Distillation, Learning approach, Model compression, Network Architecture, learning capability