TOWARDS EXPLAINABLE CLASSIFIERS USING THE COUNTERFACTUAL APPROACH - GLOBAL EXPLANATIONS FOR DISCOVERING BIAS IN DATA - Publication - Bridge of Knowledge

Search

TOWARDS EXPLAINABLE CLASSIFIERS USING THE COUNTERFACTUAL APPROACH - GLOBAL EXPLANATIONS FOR DISCOVERING BIAS IN DATA

Abstract

The paper proposes summarized attribution-based post-hoc explanations for the detection and identification of bias in data. A global explanation is proposed, and a step-by-step framework on how to detect and test bias is introduced. Since removing unwanted bias is often a complicated and tremendous task, it is automatically inserted, instead. Then, the bias is evaluated with the proposed counterfactual approach. The obtained results are validated on a sample skin lesion dataset. Using the proposed method, a number of possible bias-causing artifacts are successfully identified and confirmed in dermoscopy images. In particular, it is confirmed that black frames have a strong influence on Convolutional Neural Network’s prediction: 22% of them changed the prediction from benign to malignant.

Citations

  • 1 3

    CrossRef

  • 0

    Web of Science

  • 9

    Scopus

Cite as

Full text

download paper
downloaded 90 times
Publication version
Accepted or Published Version
License
Creative Commons: CC-BY open in new tab

Keywords

Details

Category:
Articles
Type:
artykuły w czasopismach
Published in:
Journal of Artificial Intelligence and Soft Computing Research no. 11, pages 51 - 67,
ISSN: 2083-2567
Language:
English
Publication year:
2021
Bibliographic description:
Mikołajczyk A., Grochowski M., Kwasigroch A.: TOWARDS EXPLAINABLE CLASSIFIERS USING THE COUNTERFACTUAL APPROACH - GLOBAL EXPLANATIONS FOR DISCOVERING BIAS IN DATA// Journal of Artificial Intelligence and Soft Computing Research -Vol. 11,iss. 1 (2021), s.51-67
DOI:
Digital Object Identifier (open in new tab) 10.2478/jaiscr-2021-0004
Verified by:
Gdańsk University of Technology

seen 159 times

Recommended for you

Meta Tags