Logit-based Uncertainty Measure in Classification

Huiyu Wu; Diego Klabjan

doi:10.1109/BigData52589.2021.9672066

Logit-based Uncertainty Measure in Classification

Huiyu Wu, Diego Klabjan

Industrial Engineering and Management Sciences

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

4 Scopus citations

Abstract

We introduce a new, reliable, and agnostic uncertainty measure for classification tasks called logit uncertainty. It is based on logit outputs of neural networks. We in particular show that this new uncertainty measure yields a superior performance compared to existing uncertainty measures on different tasks, including out of sample detection and finding erroneous predictions. We analyze theoretical foundations of the measure and explore a relationship with high density regions. We also demonstrate how to test uncertainty using intermediate outputs in training of generative adversarial networks. We propose two potential ways to utilize logit-based uncertainty in real world applications, and show that the uncertainty measure outperforms.

Original language	English (US)
Title of host publication	Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021
Editors	Yixin Chen, Heiko Ludwig, Yicheng Tu, Usama Fayyad, Xingquan Zhu, Xiaohua Tony Hu, Suren Byna, Xiong Liu, Jianping Zhang, Shirui Pan, Vagelis Papalexakis, Jianwu Wang, Alfredo Cuzzocrea, Carlos Ordonez
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	948-956
Number of pages	9
ISBN (Electronic)	9781665439022
DOIs	https://doi.org/10.1109/BigData52589.2021.9672066
State	Published - 2021
Event	2021 IEEE International Conference on Big Data, Big Data 2021 - Virtual, Online, United States Duration: Dec 15 2021 → Dec 18 2021

Publication series

Name	Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021

Conference

Conference	2021 IEEE International Conference on Big Data, Big Data 2021
Country/Territory	United States
City	Virtual, Online
Period	12/15/21 → 12/18/21

Funding

We thank the Google Cloud Platform research credit program for the research credits.

Keywords

classification
machine learning
uncertainty

ASJC Scopus subject areas

Information Systems and Management
Artificial Intelligence
Computer Vision and Pattern Recognition
Information Systems

Access to Document

10.1109/BigData52589.2021.9672066

Cite this

Wu, H., & Klabjan, D. (2021). Logit-based Uncertainty Measure in Classification. In Y. Chen, H. Ludwig, Y. Tu, U. Fayyad, X. Zhu, X. T. Hu, S. Byna, X. Liu, J. Zhang, S. Pan, V. Papalexakis, J. Wang, A. Cuzzocrea, & C. Ordonez (Eds.), Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 (pp. 948-956). (Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigData52589.2021.9672066

Wu, Huiyu ; Klabjan, Diego. / Logit-based Uncertainty Measure in Classification. Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021. editor / Yixin Chen ; Heiko Ludwig ; Yicheng Tu ; Usama Fayyad ; Xingquan Zhu ; Xiaohua Tony Hu ; Suren Byna ; Xiong Liu ; Jianping Zhang ; Shirui Pan ; Vagelis Papalexakis ; Jianwu Wang ; Alfredo Cuzzocrea ; Carlos Ordonez. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 948-956 (Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021).

@inproceedings{1ab3c50a08f54b8c87172387e918801d,

title = "Logit-based Uncertainty Measure in Classification",

abstract = "We introduce a new, reliable, and agnostic uncertainty measure for classification tasks called logit uncertainty. It is based on logit outputs of neural networks. We in particular show that this new uncertainty measure yields a superior performance compared to existing uncertainty measures on different tasks, including out of sample detection and finding erroneous predictions. We analyze theoretical foundations of the measure and explore a relationship with high density regions. We also demonstrate how to test uncertainty using intermediate outputs in training of generative adversarial networks. We propose two potential ways to utilize logit-based uncertainty in real world applications, and show that the uncertainty measure outperforms.",

keywords = "classification, machine learning, uncertainty",

author = "Huiyu Wu and Diego Klabjan",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Conference on Big Data, Big Data 2021 ; Conference date: 15-12-2021 Through 18-12-2021",

year = "2021",

doi = "10.1109/BigData52589.2021.9672066",

language = "English (US)",

series = "Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "948--956",

editor = "Yixin Chen and Heiko Ludwig and Yicheng Tu and Usama Fayyad and Xingquan Zhu and Hu, {Xiaohua Tony} and Suren Byna and Xiong Liu and Jianping Zhang and Shirui Pan and Vagelis Papalexakis and Jianwu Wang and Alfredo Cuzzocrea and Carlos Ordonez",

booktitle = "Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021",

address = "United States",

}

Wu, H & Klabjan, D 2021, Logit-based Uncertainty Measure in Classification. in Y Chen, H Ludwig, Y Tu, U Fayyad, X Zhu, XT Hu, S Byna, X Liu, J Zhang, S Pan, V Papalexakis, J Wang, A Cuzzocrea & C Ordonez (eds), Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021. Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021, Institute of Electrical and Electronics Engineers Inc., pp. 948-956, 2021 IEEE International Conference on Big Data, Big Data 2021, Virtual, Online, United States, 12/15/21. https://doi.org/10.1109/BigData52589.2021.9672066

Logit-based Uncertainty Measure in Classification. / Wu, Huiyu; Klabjan, Diego.
Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021. ed. / Yixin Chen; Heiko Ludwig; Yicheng Tu; Usama Fayyad; Xingquan Zhu; Xiaohua Tony Hu; Suren Byna; Xiong Liu; Jianping Zhang; Shirui Pan; Vagelis Papalexakis; Jianwu Wang; Alfredo Cuzzocrea; Carlos Ordonez. Institute of Electrical and Electronics Engineers Inc., 2021. p. 948-956 (Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021).

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

TY - GEN

T1 - Logit-based Uncertainty Measure in Classification

AU - Wu, Huiyu

AU - Klabjan, Diego

PY - 2021

Y1 - 2021

N2 - We introduce a new, reliable, and agnostic uncertainty measure for classification tasks called logit uncertainty. It is based on logit outputs of neural networks. We in particular show that this new uncertainty measure yields a superior performance compared to existing uncertainty measures on different tasks, including out of sample detection and finding erroneous predictions. We analyze theoretical foundations of the measure and explore a relationship with high density regions. We also demonstrate how to test uncertainty using intermediate outputs in training of generative adversarial networks. We propose two potential ways to utilize logit-based uncertainty in real world applications, and show that the uncertainty measure outperforms.

AB - We introduce a new, reliable, and agnostic uncertainty measure for classification tasks called logit uncertainty. It is based on logit outputs of neural networks. We in particular show that this new uncertainty measure yields a superior performance compared to existing uncertainty measures on different tasks, including out of sample detection and finding erroneous predictions. We analyze theoretical foundations of the measure and explore a relationship with high density regions. We also demonstrate how to test uncertainty using intermediate outputs in training of generative adversarial networks. We propose two potential ways to utilize logit-based uncertainty in real world applications, and show that the uncertainty measure outperforms.

KW - classification

KW - machine learning

KW - uncertainty

UR - http://www.scopus.com/inward/record.url?scp=85125362347&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85125362347&partnerID=8YFLogxK

U2 - 10.1109/BigData52589.2021.9672066

DO - 10.1109/BigData52589.2021.9672066

M3 - Conference contribution

AN - SCOPUS:85125362347

T3 - Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021

SP - 948

EP - 956

BT - Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021

A2 - Chen, Yixin

A2 - Ludwig, Heiko

A2 - Tu, Yicheng

A2 - Fayyad, Usama

A2 - Zhu, Xingquan

A2 - Hu, Xiaohua Tony

A2 - Byna, Suren

A2 - Liu, Xiong

A2 - Zhang, Jianping

A2 - Pan, Shirui

A2 - Papalexakis, Vagelis

A2 - Wang, Jianwu

A2 - Cuzzocrea, Alfredo

A2 - Ordonez, Carlos

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE International Conference on Big Data, Big Data 2021

Y2 - 15 December 2021 through 18 December 2021

ER -

Wu H, Klabjan D. Logit-based Uncertainty Measure in Classification. In Chen Y, Ludwig H, Tu Y, Fayyad U, Zhu X, Hu XT, Byna S, Liu X, Zhang J, Pan S, Papalexakis V, Wang J, Cuzzocrea A, Ordonez C, editors, Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 948-956. (Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021). doi: 10.1109/BigData52589.2021.9672066

Logit-based Uncertainty Measure in Classification

Abstract

Publication series

Conference

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this