Leveraging Causal Relations to Provide Counterfactual Explanations and Feasible Recommendations to End Users

Riccardo Crupi, Beatriz San Miguel González, Alessandro Castelnovo, Daniele Regoli

2022

Abstract

Over the last years, there has been a growing debate on the ethical issues of Artificial Intelligence (AI). Explainable Artificial Intelligence (XAI) has appeared as a key element to enhance trust of AI systems from both technological and human-understandable perspectives. In this sense, counterfactual explanations are becoming a de facto solution for end users to assist them in acting to achieve a desired outcome. In this paper, we present a new method called Counterfactual Explanations as Interventions in Latent Space (CEILS) to generate explanations focused on the production of feasible user actions. The main features of CEILS are: it takes into account the underlying causal relations by design, and can be set on top of an arbitrary counterfactual explanation generator. We demonstrate how CEILS succeeds through its evaluation on a real dataset of the financial domain.

Paper Citation

in Harvard Style

Crupi R., San Miguel González B., Castelnovo A. and Regoli D. (2022). Leveraging Causal Relations to Provide Counterfactual Explanations and Feasible Recommendations to End Users. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-547-0, pages 24-32. DOI: 10.5220/0010761500003116

in Bibtex Style

@conference{icaart22,
author={Riccardo Crupi and Beatriz San Miguel González and Alessandro Castelnovo and Daniele Regoli},
title={Leveraging Causal Relations to Provide Counterfactual Explanations and Feasible Recommendations to End Users},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2022},
pages={24-32},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010761500003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Leveraging Causal Relations to Provide Counterfactual Explanations and Feasible Recommendations to End Users
SN - 978-989-758-547-0
AU - Crupi R.
AU - San Miguel González B.
AU - Castelnovo A.
AU - Regoli D.
PY - 2022
SP - 24
EP - 32
DO - 10.5220/0010761500003116