DiPACE: Diverse, Plausible and Actionable Counterfactual Explanations

Jacob Sanderson, Hua Mao, Wai Lok Woo

2025

Abstract

As Artificial Intelligence (AI) becomes integral to high-stakes applications, the need for interpretable and trustworthy decision-making tools is increasingly essential. Counterfactual Explanations (CFX) offer an effective approach, allowing users to explore “what if?” scenarios that highlight actionable changes for achieving more desirable outcomes. Existing CFX methods often prioritize select qualities, such as diversity, plausibility, proximity, or sparsity, but few balance all four in a flexible way. This work introduces DiPACE, a practical CFX framework that balances these qualities while allowing users to adjust parameters according to specific application needs. DiPACE also incorporates a penalty-based adjustment to refine results toward user-defined thresholds. Experimental results on real-world datasets demonstrate that DiPACE consistently outperforms existing methods Wachter, DiCE and CARE in achieving diverse, realistic, and actionable CFs, with strong performance across all four characteristics. The findings confirm DiPACE’s utility as a user-adaptable, interpretable CFX tool suitable for diverse AI applications, with a robust balance of qualities that enhances both feasibility and trustworthiness in decision-making contexts.

Paper Citation

in Harvard Style

Sanderson J., Mao H. and Woo W. (2025). DiPACE: Diverse, Plausible and Actionable Counterfactual Explanations. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 543-554. DOI: 10.5220/0013219100003890

in Bibtex Style

@conference{icaart25,
author={Jacob Sanderson and Hua Mao and Wai Woo},
title={DiPACE: Diverse, Plausible and Actionable Counterfactual Explanations},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={543-554},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013219100003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - DiPACE: Diverse, Plausible and Actionable Counterfactual Explanations
SN - 978-989-758-737-5
AU - Sanderson J.
AU - Mao H.
AU - Woo W.
PY - 2025
SP - 543
EP - 554
DO - 10.5220/0013219100003890
PB - SciTePress