Transport-based Counterfactual Models - Méthodes et Ingénierie des Langues, des Ontologies et du Discours Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Transport-based Counterfactual Models

Résumé

Counterfactual frameworks have grown popular in explainable and fair machine learning, as they offer a natural notion of causation. However, state-of-the-art models to compute counterfactuals are either unrealistic or unfeasible. In particular, while Pearl's causal inference provides appealing rules to calculate counterfactuals, it relies on a model that is unknown and hard to discover in practice. We address the problem of designing realistic and feasible counterfactuals in the absence of a causal model. We define transport-based counterfactual models as collections of joint probability distributions between observable distributions, and show their connection to causal counterfactuals. More specifically, we argue that optimal transport theory defines relevant transport-based counterfactual models, as they are numerically feasible, statistically-faithful, and can even coincide with causal counterfactual models. We illustrate the practicality of these models by defining sharper fairness criteria than typical group fairness conditions.
Fichier principal
Vignette du fichier
TBCF.pdf (302.44 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03216124 , version 1 (04-05-2021)
hal-03216124 , version 2 (28-08-2021)
hal-03216124 , version 3 (06-01-2023)

Identifiants

Citer

Lucas de Lara, Alberto González-Sanz, Nicholas Asher, Jean-Michel Loubes. Transport-based Counterfactual Models. 2021. ⟨hal-03216124v2⟩
512 Consultations
602 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More