Meta Pattern Concern Score: A Novel Evaluation Measure with Human Values for Multi-classifiers

Yanyun Wang, Dehui Du, Yuanhao Liu

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

Abstract

While advanced classifiers have been increasingly used in real-world safety-critical applications, how to properly evaluate the black-box models given specific human values remains a concern in the community. Such human values include punishing error cases of different severity in varying degrees and making compromises in general performance to reduce specific dangerous cases. In this paper, we propose a novel evaluation measure named Meta Pattern Concern Score based on the abstract representation of probabilistic prediction and the adjustable threshold for the concession in prediction confidence, to introduce the human values into multi-classifiers. Technically, we learn from the advantages and disadvantages of two kinds of common metrics, namely the confusion matrix-based evaluation measures and the loss values, so that our measure is effective as them even under general tasks, and the cross entropy loss becomes a special case of our measure in the limit. Besides, our measure can also be used to refine the model training by dynamically adjusting the learning rate. The experiments on four kinds of models and six datasets confirm the effectiveness and efficiency of our measure. And a case study shows it can not only find the ideal model reducing 0.53% of dangerous cases by only sacrificing 0.04% of training accuracy, but also refine the learning rate to train a new model averagely outperforming the original one with a 1.62% lower value of itself and 0.36% fewer number of dangerous cases.

Original languageEnglish
Title of host publication2023 IEEE International Conference on Systems, Man, and Cybernetics
Subtitle of host publicationImproving the Quality of Life, SMC 2023 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages597-604
Number of pages8
ISBN (Electronic)9798350337020
DOIs
StatePublished - 2023
Event2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023 - Hybrid, Honolulu, United States
Duration: 1 Oct 20234 Oct 2023

Publication series

NameConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
ISSN (Print)1062-922X

Conference

Conference2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023
Country/TerritoryUnited States
CityHybrid, Honolulu
Period1/10/234/10/23

Fingerprint

Dive into the research topics of 'Meta Pattern Concern Score: A Novel Evaluation Measure with Human Values for Multi-classifiers'. Together they form a unique fingerprint.

Cite this