Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/42954
Title: | Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps | Authors: | Grau, Isel NAPOLES RUIZ, Gonzalo Hoitsma, Fabian KOUTSOVITI-KOUMERI, Lisa VANHOOF, Koen |
Issue Date: | 2024 | Publisher: | Springer | Source: | Springer, p. 745 -764 | Series/Report: | Lecture Notes in Networks and Systems | 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. | Keywords: | Fairness;Implicit Bias;Explainable artificial intelligence;Feature importance;Fuzzy cognitive maps | Document URI: | http://hdl.handle.net/1942/42954 | ISBN: | 978-3-031-47720-1 978-3-031-47721-8 |
DOI: | 10.1007/978-3-031-47721-8_50 | ISI #: | 001261691200050 | Datasets of the publication: | 10.24432/C5NC77 | Category: | C1 | Type: | Proceedings Paper |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Pages from 978-3-031-47721-8.pdf Restricted Access | Published version | 775.59 kB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.