CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows
About
Counterfactual explanation is a form of interpretable machine learning that generates perturbations on a sample to achieve the desired outcome. The generated samples can act as instructions to guide end users on how to observe the desired results by altering samples. Although state-of-the-art counterfactual explanation methods are proposed to use variational autoencoder (VAE) to achieve promising improvements, they suffer from two major limitations: 1) the counterfactuals generation is prohibitively slow, which prevents algorithms from being deployed in interactive environments; 2) the counterfactual explanation algorithms produce unstable results due to the randomness in the sampling procedure of variational autoencoder. In this work, to address the above limitations, we design a robust and efficient counterfactual explanation framework, namely CeFlow, which utilizes normalizing flows for the mixed-type of continuous and categorical features. Numerical experiments demonstrate that our technique compares favorably to state-of-the-art methods. We release our source at https://github.com/tridungduong16/fairCE.git for reproducing the results.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Counterfactual Explanations | COMPAS | Validity38.5 | 21 | |
| Counterfactual Explanations | moons | Validity99.1 | 19 | |
| Counterfactual Explanations | HELOC | Validity54.2 | 19 | |
| Counterfactual Explanation Plausibility | Spirals | LOF Score1.25 | 5 | |
| Counterfactual Explanations | chessboard | Cost0.804 | 5 | |
| Counterfactual Explanations | Spirals | Cost0.895 | 5 | |
| Counterfactual Explanations | blood | Cost1.556 | 5 | |
| Counterfactual Explanation | Adult | Cost3.959 | 5 | |
| Counterfactual Explanations | circles | Cost1.195 | 5 |