Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps

Isel Grau, Gonzalo Nápoles, Fabian Hoitsma, Lisa Koutsoviti Koumeri (Corresponding author), Koen Vanhoof

Research output: Contribution to journalArticleAcademic

66 Downloads (Pure)

Abstract

In this paper, we integrate the concepts of feature importance with implicit bias in the context of pattern classification. This is done by means of a three-step methodology that involves (i) building a classifier and tuning its hyperparameters, (ii) building a Fuzzy Cognitive Map model able to quantify implicit bias, and (iii) using the SHAP feature importance to active the neural concepts when performing simulations. The results using a real case study concerning fairness research support our two-fold hypothesis. On the one hand, it is illustrated the risks of using a feature importance method as an absolute tool to measure implicit bias. On the other hand, it is concluded that the amount of bias towards protected features might differ depending on whether the features are numerically or categorically encoded.
Original languageEnglish
Article number2305.09399v2
Pages (from-to)1-20
Number of pages20
JournalarXiv
Volume2023
DOIs
Publication statusPublished - 2023

Fingerprint

Dive into the research topics of 'Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps'. Together they form a unique fingerprint.
  • Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps

    Grau, I., Nápoles, G., Hoitsma, F., Koumeri, L. K. & Vanhoof, K., 10 Jan 2024, Intelligent Systems and Applications: Proceedings of the 2023 Intelligent Systems Conference (IntelliSys) Volume 1. Arai, K. (ed.). Cham: Springer, p. 745-764 20 p. (Lecture Notes in Networks and Systems (LNNS); vol. 822).

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

    Open Access
    File
    1 Citation (Scopus)

Cite this