Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Probabilistically Plausible Counterfactual Explanations with Normalizing Flows

About

We present PPCEF, a novel method for generating probabilistically plausible counterfactual explanations (CFs). PPCEF advances beyond existing methods by combining a probabilistic formulation that leverages the data distribution with the optimization of plausibility within a unified framework. Compared to reference approaches, our method enforces plausibility by directly optimizing the explicit density function without assuming a particular family of parametrized distributions. This ensures CFs are not only valid (i.e., achieve class change) but also align with the underlying data's probability density. For that purpose, our approach leverages normalizing flows as powerful density estimators to capture the complex high-dimensional data distribution. Furthermore, we introduce a novel loss that balances the trade-off between achieving class change and maintaining closeness to the original instance while also incorporating a probabilistic plausibility term. PPCEF's unconstrained formulation allows for efficient gradient-based optimization with batch processing, leading to orders of magnitude faster computation compared to prior methods. Moreover, the unconstrained formulation of PPCEF allows for the seamless integration of future constraints tailored to specific counterfactual properties. Finally, extensive evaluations demonstrate PPCEF's superiority in generating high-quality, probabilistically plausible counterfactual explanations in high-dimensional tabular settings. This makes PPCEF a powerful tool for not only interpreting complex machine learning models but also for improving fairness, accountability, and trust in AI systems.

Patryk Wielopolski, Oleksii Furman, Jerzy Stefanowski, Maciej Zi\k{e}ba• 2024

Related benchmarks

TaskDatasetResultRank
Counterfactual Explanationsmoons
Validity100
19
Counterfactual ExplanationsHELOC
Validity99.3
19
Counterfactual ExplanationsLaw
Validity100
18
Counterfactual Explanation GenerationBlobs
Validity100
17
Counterfactual Explanation GenerationDigits
Validity100
17
Counterfactual Explanation GenerationWine
Validity1
17
Counterfactual ExplanationMoons 5-fold synthetic (test)
Validity100
14
Local Counterfactual ExplanationsWine
Validity1
8
Counterfactual ExplanationDiabetes 5-fold (test)
Validity99.9
7
Counterfactual ExplanationsHELOC original (test)
Validity99.6
7
Showing 10 of 16 rows

Other info

Follow for update