Natural Counterfactuals With Necessary Backtracking

Author:

Guang-Yuan Hao, Jiji Zhang, Biwei Huang, Hao Wang, Kun Zhang

Keyword:

Computer Science, Artificial Intelligence, Artificial Intelligence (cs.AI), Machine Learning (cs.LG), Methodology (stat.ME)

journal:

date:

2024-02-02 00:00:00

Abstract

Counterfactual reasoning is pivotal in human cognition and especially important for providing explanations and making decisions. While Judea Pearl's influential approach is theoretically elegant, its generation of a counterfactual scenario often requires interventions that are too detached from the real scenarios to be feasible. In response, we propose a framework of natural counterfactuals and a method for generating counterfactuals that are natural with respect to the actual world's data distribution. Our methodology refines counterfactual reasoning, allowing changes in causally preceding variables to minimize deviations from realistic scenarios. To generate natural counterfactuals, we introduce an innovative optimization framework that permits but controls the extent of backtracking with a naturalness criterion. Empirical experiments indicate the effectiveness of our method.

PDF: Natural Counterfactuals With Necessary Backtracking.pdf