Skip to main content

Research Repository

Advanced Search

Actionable feature discovery in counterfactuals using feature relevance explainers.

Wiratunga, Nirmalie; Wijekoon, Anjana; Nkisi-Orji, Ikechukwu; Martin, Kyle; Palihawadana, Chamath; Corsar, David

Authors



Contributors

Hayley Borck
Editor

Viktor Eisenstadt
Editor

Antonio Sánchez-Ruiz
Editor

Michael Floyd
Editor

Abstract

Counterfactual explanations focus on 'actionable knowledge' to help end-users understand how a Machine Learning model outcome could be changed to a more desirable outcome. For this purpose a counterfactual explainer needs to be able to reason with similarity knowledge in order to discover input dependencies that relate to outcome changes. Identifying the minimum subset of feature changes to action a change in the decision is an interesting challenge for counterfactual explainers. In this paper we show how feature relevance based explainers (i.e. LIME, SHAP), can inform a counterfactual explainer to identify the minimum subset of 'actionable features'. We demonstrate our DisCERN (Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods) algorithm on three datasets and compare against the widely used counterfactual approach DiCE. Our preliminary results show that DisCERN to be a viable strategy that should be adopted to minimise the actionable changes.

Citation

WIRATUNGA, N., WIJEKOON, A., NKISI-ORJI, I., MARTIN, K., PALIHAWADANA, C. and CORSAR, D. 2021. Actionable feature discovery in counterfactuals using feature relevance explainers. In Borck, H., Eisenstadt, V., Sánchez-Ruiz, A. and Floyd, M. (eds.) ICCBR 2021 workshop proceedings (ICCBR-WS 2021): workshop proceedings for the 29th International conference on case-based reasoning co-located with the 29th International conference on case-case based reasoning (ICCBR 2021), 13-16 September 2021, Salamanca, Spain [virtual conference]. CEUR-WS proceedings, 3017. Aachen: CEUR-WS [online], pages 63-74. Available from: http://ceur-ws.org/Vol-3017/101.pdf

Conference Name 29th International conference on case-based reasoning workshops 2021 (ICCBR-WS 2021), co-located with the 29th International conference on case-case based reasoning (ICCBR 2021)
Conference Location Salamanca, Spain [virtual conference]
Start Date Sep 13, 2021
End Date Sep 16, 2021
Acceptance Date Jun 11, 2021
Online Publication Date Sep 16, 2021
Publication Date Nov 24, 2021
Deposit Date Jan 6, 2022
Publicly Available Date Jan 6, 2022
Publisher CEUR Workshop Proceedings
Volume 3017
Pages 63-74
Series ISSN 1613-0073
Book Title ICCBR 2021 workshop proceedings (ICCBR-WS 2021): workshop proceedings for the 29th International conference on case-based reasoning co-located with the 29th International conference on case-case based reasoning (ICCBR 2021)
Keywords Explainable AI; Counterfactual; Feature relevance; Actionable features
Public URL https://rgu-repository.worktribe.com/output/1563535
Publisher URL http://ceur-ws.org/Vol-3017/101.pdf

Files





You might also like



Downloadable Citations