Improving the interpretability of deep neural networks with knowledge distillation

Xuan Liu; Xiaoguang Wang; Stan Matwin

doi:10.1109/ICDMW.2018.00132

Improving the interpretability of deep neural networks with knowledge distillation

Xuan Liu, Xiaoguang Wang, Stan Matwin

Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

71 Citations (Scopus)

Original language	English
Title of host publication	Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018
Editors	Hanghang Tong, Zhenhui Li, Feida Zhu, Jeffrey Yu
Publisher	IEEE Computer Society
Pages	905-912
Number of pages	8
ISBN (Electronic)	9781538692882
DOIs	https://doi.org/10.1109/ICDMW.2018.00132
Publication status	Published - Jul 2 2018
Event	18th IEEE International Conference on Data Mining Workshops, ICDMW 2018 - Singapore, Singapore Duration: Nov 17 2018 → Nov 20 2018

Publication series

Name	IEEE International Conference on Data Mining Workshops, ICDMW
Volume	2018-November
ISSN (Print)	2375-9232
ISSN (Electronic)	2375-9259

Conference

Conference	18th IEEE International Conference on Data Mining Workshops, ICDMW 2018
Country/Territory	Singapore
City	Singapore
Period	11/17/18 → 11/20/18

ASJC Scopus Subject Areas

Software
Computer Science Applications

Keywords

Decision Tree
Neural Networks
TensorFlow
dark knowledge
interpretation
knowledge distillation

Access to Document

10.1109/ICDMW.2018.00132

Cite this

Liu, X., Wang, X., & Matwin, S. (2018). Improving the interpretability of deep neural networks with knowledge distillation. In H. Tong, Z. Li, F. Zhu, & J. Yu (Eds.), Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018 (pp. 905-912). Article 8637552 (IEEE International Conference on Data Mining Workshops, ICDMW; Vol. 2018-November). IEEE Computer Society. https://doi.org/10.1109/ICDMW.2018.00132

Improving the interpretability of deep neural networks with knowledge distillation. / Liu, Xuan; Wang, Xiaoguang; Matwin, Stan.
Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018. ed. / Hanghang Tong; Zhenhui Li; Feida Zhu; Jeffrey Yu. IEEE Computer Society, 2018. p. 905-912 8637552 (IEEE International Conference on Data Mining Workshops, ICDMW; Vol. 2018-November).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Liu, X, Wang, X & Matwin, S 2018, Improving the interpretability of deep neural networks with knowledge distillation. in H Tong, Z Li, F Zhu & J Yu (eds), Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018., 8637552, IEEE International Conference on Data Mining Workshops, ICDMW, vol. 2018-November, IEEE Computer Society, pp. 905-912, 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018, Singapore, Singapore, 11/17/18. https://doi.org/10.1109/ICDMW.2018.00132

Liu X, Wang X, Matwin S. Improving the interpretability of deep neural networks with knowledge distillation. In Tong H, Li Z, Zhu F, Yu J, editors, Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018. IEEE Computer Society. 2018. p. 905-912. 8637552. (IEEE International Conference on Data Mining Workshops, ICDMW). doi: 10.1109/ICDMW.2018.00132

Liu, Xuan ; Wang, Xiaoguang ; Matwin, Stan. / Improving the interpretability of deep neural networks with knowledge distillation. Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018. editor / Hanghang Tong ; Zhenhui Li ; Feida Zhu ; Jeffrey Yu. IEEE Computer Society, 2018. pp. 905-912 (IEEE International Conference on Data Mining Workshops, ICDMW).

@inproceedings{8cb64cb35e6b4c41b628afaec12a1731,

title = "Improving the interpretability of deep neural networks with knowledge distillation",

keywords = "Decision Tree, Neural Networks, TensorFlow, dark knowledge, interpretation, knowledge distillation",

author = "Xuan Liu and Xiaoguang Wang and Stan Matwin",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018 ; Conference date: 17-11-2018 Through 20-11-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/ICDMW.2018.00132",

language = "English",

series = "IEEE International Conference on Data Mining Workshops, ICDMW",

publisher = "IEEE Computer Society",

pages = "905--912",

editor = "Hanghang Tong and Zhenhui Li and Feida Zhu and Jeffrey Yu",

booktitle = "Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018",

address = "United States",

}

TY - GEN

T1 - Improving the interpretability of deep neural networks with knowledge distillation

AU - Liu, Xuan

AU - Wang, Xiaoguang

AU - Matwin, Stan

PY - 2018/7/2

Y1 - 2018/7/2

KW - Decision Tree

KW - Neural Networks

KW - TensorFlow

KW - dark knowledge

KW - interpretation

KW - knowledge distillation

UR - http://www.scopus.com/inward/record.url?scp=85062886614&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062886614&partnerID=8YFLogxK

U2 - 10.1109/ICDMW.2018.00132

DO - 10.1109/ICDMW.2018.00132

M3 - Conference contribution

AN - SCOPUS:85062886614

T3 - IEEE International Conference on Data Mining Workshops, ICDMW

SP - 905

EP - 912

BT - Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018

A2 - Tong, Hanghang

A2 - Li, Zhenhui

A2 - Zhu, Feida

A2 - Yu, Jeffrey

PB - IEEE Computer Society

T2 - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018

Y2 - 17 November 2018 through 20 November 2018

ER -

Improving the interpretability of deep neural networks with knowledge distillation

Publication series

Conference

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this