DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation

2024/06/02 by Yinjun Wu, Mayank Keoliya, Wu, Yinjun +17 · 2 citations
Computer Science · Mathematics · #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Healthcare #Methodology (stat.ME) #Statistical Methods in Clinical Trials

paper · doi:10.48550/arxiv.2406.00611

openalex publication_date 2024/06/02 · openalex created_date 2024/06/06 · openalex updated_date 2026/08/01

Abstract

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.

Citations

• The Cancer Genome Atlas Pan-Cancer analysis project

Cited by

• The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models
• Direct Preference Optimization for Adaptive Concept-based Explanations

Related

• Learning Interpretable Models with Causal Guarantees
• Causal Rule Forest: Toward Interpretable and Precise Treatment Effect Estimation
• Causal Effect Estimation: Recent Advances, Challenges, and Opportunities
• A Large Scale Benchmark for Individual Treatment Effect Prediction and Uplift Modeling
• Technical Report: Facilitating the Adoption of Causal Inference Methods Through LLM-Empowered Co-Pilot