paper-with-me

홈 › Papers

Measuring axiomatic soundness of counterfactual image models

2023-03-02 · Miguel Monteiro, Fabio De Sousa Ribeiro, Nick Pawlowski, Daniel C. Castro, Ben Glocker

We present a general framework for evaluating image counterfactuals. The power and flexibility of deep generative models make them valuable tools for learning mechanisms in structural causal models. However, their flexibility makes counterfactual identifiability impossible in the general case. Motivated by these issues, we revisit Pearl's axiomatic definition of counterfactuals to determine the necessary constraints of any counterfactual inference model: composition, reversibility, and effectiveness. We frame counterfactuals as functions of an input variable, its parents, and counterfactual parents and use the axiomatic constraints to restrict the set of functions that could represent the counterfactual, thus deriving distance metrics between the approximate and ideal functions. We demonstrate how these metrics can be used to compare and choose between different approximate counterfactual inference models and to provide insight into a model's shortcomings and trade-offs.

📄 PDF Abstract BibTeX arXiv:2303.01274

Code (1)

biomedia-mira/causal-gen pytorch

Tasks

counterfactualCounterfactual Inference

Methods 이 논문이 사용한 방법론

Counterfactuals 설명 없음

Similar Papers 제목 키워드 기반

High Fidelity Image Counterfactuals with Probabilistic Causal Models

2023-06-27 · Fabio De Sousa Ribeiro, Tian Xia, Miguel Monteiro, Nick Pawlowski 외

We present a general causal generative modelling framework for accurate estimation of high fidelity image counterfactuals with deep structural causal models. Estimation of interventional and counterfactual queries for hi…

counterfactual

Counterfactual Identifiability via Dynamic Optimal Transport

2025-10-09 · Fabio De Sousa Ribeiro, Ainkaran Santhirasekaram, Ben Glocker arxiv

We address the open question of counterfactual identification for high-dimensional multivariate outcomes from observational data. Pearl (2000) argues that counterfactuals must be identifiable (i.e., recoverable from the …

Axiomatic Foundations of Counterfactual Explanations

2026-02-03 · Leila Amgoud, Martin Cooper arxiv

Explaining autonomous and intelligent systems is critical in order to improve trust in their decisions. Counterfactuals have emerged as one of the most compelling forms of explanation. They address ``why not'' questions …

Combining Counterfactuals With Shapley Values To Explain Image Models

2022-06-14 · Aditya Lahiri, Kamran Alipour, Ehsan Adeli, Babak Salimi

With the widespread use of sophisticated machine learning models in sensitive applications, understanding their decision-making has become an essential task. Models trained on tabular data have witnessed significant prog…

Decision MakingExplainable Artificial Intelligence (XAI)

Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examples

2026-03-02 · Phillip Howard, Xin Su, Kathleen C. Fraser arxiv

Large Vision-Language Models (LVLMs) have grown increasingly powerful in recent years, but can also exhibit harmful biases. Prior studies investigating such biases have primarily focused on demographic traits related to …