VCNet: A self-explaining model for realistic counterfactual generation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

VCNet: A self-explaining model for realistic counterfactual generation

Abstract

Counterfactual explanation is a common class of methods to make local explanations of machine learning decisions. For a given instance, these methods aim to find the smallest modification of feature values that changes the predicted decision made by a machine learning model. One of the challenges of counterfactual explanation is the efficient generation of realistic counterfactuals. To address this challenge, we propose VCNet-Variational Counter Net-a model architecture that combines a predictor and a counterfactual generator that are jointly trained, for regression or classification tasks. VCNet is able to both generate predictions, and to generate counterfactual explanations without having to solve another minimisation problem. Our contribution is the generation of counterfactuals that are close to the distribution of the predicted class. This is done by learning a variational autoencoder conditionally to the output of the predictor in a join-training fashion. We present an empirical evaluation on tabular datasets and across several interpretability metrics. The results are competitive with the state-of-the-art method.
Fichier principal
Vignette du fichier
main.pdf (722.05 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03899151 , version 1 (14-12-2022)

Licence

Attribution

Identifiers

Cite

Victor Guyomard, Françoise Fessant, Thomas Guyet, Tassadit Bouadi, Alexandre Termier. VCNet: A self-explaining model for realistic counterfactual generation. ECML PKDD 2022 - European Conference on Machine Learning and Knowledge Discovery in Databases., Sep 2022, Grenoble, France. pp.1-16. ⟨hal-03899151⟩
39 View
33 Download

Altmetric

Share

Gmail Facebook X LinkedIn More