Logit-based Uncertainty Measure in Classification

Huiyu Wu, Diego Klabjan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations


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 languageEnglish (US)
Title of host publicationProceedings - 2021 IEEE International Conference on Big Data, Big Data 2021
EditorsYixin 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
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages9
ISBN (Electronic)9781665439022
StatePublished - 2021
Event2021 IEEE International Conference on Big Data, Big Data 2021 - Virtual, Online, United States
Duration: Dec 15 2021Dec 18 2021

Publication series

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


Conference2021 IEEE International Conference on Big Data, Big Data 2021
Country/TerritoryUnited States
CityVirtual, Online


  • classification
  • machine learning
  • uncertainty

ASJC Scopus subject areas

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


Dive into the research topics of 'Logit-based Uncertainty Measure in Classification'. Together they form a unique fingerprint.

Cite this