Skip to main content

Research Repository

Advanced Search

DisCERN: discovering counterfactual explanations using relevance features from neighbourhoods.

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

Authors



Abstract

Counterfactual explanations focus on 'actionable knowledge' to help end-users understand how a machine learning outcome could be changed to a more desirable outcome. For this purpose a counterfactual explainer needs to discover input dependencies that relate to outcome changes. Identifying the minimum subset of feature changes needed to action an output change in the decision is an interesting challenge for counterfactual explainers. The DisCERN algorithm introduced in this paper is a case-based counter-factual explainer. Here counterfactuals are formed by replacing feature values from a nearest unlike neighbour (NUN) until an actionable change is observed. We show how widely adopted feature relevance-based explainers (i.e. LIME, SHAP), can inform DisCERN to identify the minimum subset of 'actionable features'. We demonstrate our DisCERN algorithm on five datasets in a comparative study with the widely used optimisation-based counterfactual approach DiCE. Our results demonstrate that DisCERN is an effective strategy to minimise actionable changes necessary to create good counterfactual explanations.

Citation

WIRATUNGA, N., WIJEKOON, A., NKISI-ORJI, I., MARTIN, K., PALIHAWADANA, C. and CORSAR, D. 2021. DisCERN: discovering counterfactual explanations using relevance features from neighbourhoods. To be presented at 33rd IEEE (Institute of Electrical and Electronics Engineers) International conference on tools with artificial intelligence 2021 (ICTAI 2021), 1-3 November 2021, [virtual conference].

Conference Name 33rd IEEE (Institute of Electrical and Electronics Engineers) International conference on tools with artificial intelligence 2021 (ICTAI 2021)
Conference Location [virtual conference]
Start Date Nov 1, 2021
End Date Nov 3, 2021
Acceptance Date Sep 10, 2021
Deposit Date Sep 16, 2021
Publicly Available Date Sep 16, 2021
Publisher IEEE Computer Society
Keywords Explainable AI; Counterfactuals; Case-based reasoning
Public URL https://rgu-repository.worktribe.com/output/1457005

Files

WIRATUNGA 2021 DisCERN (666 Kb)
PDF

Copyright Statement
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.







You might also like



Downloadable Citations