Loading...
Natural Counterfactuals With Necessary Backtracking
Hao, Guang-Yuan Zhang, Jiji Huang, Biwei Wang, Hao Zhang, Kun
Hao, Guang-Yuan
Zhang, Jiji
Huang, Biwei
Wang, Hao
Zhang, Kun
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2024
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
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 too much deviation from the observed scenarios to be feasible, as we show using simple examples. To mitigate this difficulty, we propose a framework of natural counterfactuals and a method for generating counterfactuals that are more feasible with respect to the actual data distribution. Our methodology incorporates a certain amount of backtracking when needed, allowing changes in causally preceding variables to minimize deviations from realistic scenarios. Specifically, we introduce a novel optimization framework that permits but also controls the extent of backtracking with a "naturalness'' criterion. Empirical experiments demonstrate the effectiveness of our method. The code is available at https://github.com/GuangyuanHao/natural_counterfactuals.
Citation
G.-Y. Hao, J. Zhang, B. Huang, H. Wang, and K. Zhang, “Natural Counterfactuals With Necessary Backtracking,” Adv Neural Inf Process Syst, vol. 37, pp. 14962–14995, Dec. 2024.
Source
Advances in Neural Information Processing Systems (NeurIPS 2024)
Conference
Keywords
Natural counterfactuals, Necessary backtracking, Counterfactual reasoning, Structural causal models, Optimization framework
Subjects
Source
Publisher
NEURIPS