DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation

Authors

• Yinjun Wu
• Mayank Keoliya
• Kan Chen
• Neelay Velingker
• Ziyang Li
• Emily J Getzen
• Qi Long
• Mayur Naik
• Ravi B Parikh
• Eric Wong

Language

English

Publication Date

7-1-2024

Journal

Proceedings of Machine Learning Research

PMID

39205826

PMCID

PMC11350397

PubMedCentral® Posted Date

8-28-2024

PubMedCentral® Full Text Version

Author MSS

Abstract

Designing faithful yet accurate AI models is challenging, particularly in the field of individual treatment effect estimation (ITE). ITE prediction models deployed in critical settings such as healthcare should ideally be (i) accurate, and (ii) provide faithful explanations. However, current solutions are inadequate: state-of-the-art black-box models do not supply explanations, post-hoc explainers for black-box models lack faithfulness guarantees, and self-interpretable models greatly compromise accuracy. To address these issues, we propose DISCRET, a self-interpretable ITE framework that synthesizes faithful, rule-based explanations for each sample. A key insight behind DISCRET is that explanations can serve dually as database queries to identify similar subgroups of samples. We provide a novel RL algorithm to efficiently synthesize these explanations from a large search space. We evaluate DISCRET on diverse tasks involving tabular, image, and text data. DISCRET outperforms the best self-interpretable models and has accuracy comparable to the best black-box models while providing faithful explanations. DISCRET is available at https://github.com/wuyinjun-1993/DISCRET-ICML2024.

Published Open-Access

yes

Recommended Citation

Wu, Yinjun; Keoliya, Mayank; Chen, Kan; et al., "DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation" (2024). Faculty, Staff and Student Publications. 929.
https://digitalcommons.library.tmc.edu/uthshis_docs/929