<abstract xmlns="http://www.w3.org/1999/xhtml"><p>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.</p></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.

Towards Explainable Classifiers Using the Counterfactual Approach - Global Explanations for Discovering Bias in Data

Department of Electrical Engineering, Control Systems and Informatics

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

The paper proposes summarized attribution-based post-hoc explanations for the detection and identification of bias in data. A global explanation is proposed,...

Towards Explainable Classifiers Using the Counterfactual Approach - Global Explanations for Discovering Bias in Data

Pubblicato online: 03 dic 2020

Pagine: 51 - 67

Ricevuto: 15 mag 2020

Accettato: 30 set 2020

DOI: https://doi.org/10.2478/jaiscr-2021-0004

Parole chiave
explainable classifiers, counterfactual approach, bias detection

© 2021 Agnieszka Mikołajczyk et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Towards Explainable Classifiers Using the Counterfactual Approach - Global Explanations for Discovering Bias in Data

Pubblicato online: 03 dic 2020

Pagine: 51 - 67

Ricevuto: 15 mag 2020

Accettato: 30 set 2020

DOI: https://doi.org/10.2478/jaiscr-2021-0004

Parole chiaveexplainable classifiers, counterfactual approach, bias detection

© 2021 Agnieszka Mikołajczyk et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Parole chiave
explainable classifiers, counterfactual approach, bias detection