paper-with-me

홈 › Papers

Prime Implicant Explanations for Reaction Feasibility Prediction

2025-10-10 · Klaus Weinbauer, Tieu-Long Phan, Peter F. Stadler, Thomas Gärtner, Sagar Malhotra arxiv

Machine learning models that predict the feasibility of chemical reactions have become central to automated synthesis planning. Despite their predictive success, these models often lack transparency and interpretability. We introduce a novel formulation of prime implicant explanations--also known as minimally sufficient reasons--tailored to this domain, and propose an algorithm for computing such explanations in small-scale reaction prediction tasks. Preliminary experiments demonstrate that our notion of prime implicant explanations conservatively captures the ground truth explanations. That is, such explanations often contain redundant bonds and atoms but consistently capture the molecular attributes that are essential for predicting reaction feasibility.

📄 PDF Abstract BibTeX arXiv:2510.09226

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On the Complexity of Enumerating Prime Implicants from Decision-DNNF Circuits

2023-01-30 · Alexis de Colnet, Pierre Marquis

We consider the problem EnumIP of enumerating prime implicants of Boolean functions represented by decision decomposable negation normal form (dec-DNNF) circuits. We study EnumIP from dec-DNNF within the framework of enu…

Negation

A New Class of Explanations for Classifiers with Non-Binary Features

2023-04-28 · Chunxi Ji, Adnan Darwiche

Two types of explanations have been receiving increased attention in the literature when analyzing the decisions made by classifiers. The first type explains why a decision was made and is known as a sufficient reason fo…

counterfactualCounterfactual Explanation

Trading Complexity for Sparsity in Random Forest Explanations

2021-08-11 · NeurIPS 2021 12 · Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche 외

Random forests have long been considered as powerful model ensembles in machine learning. By training multiple decision trees, whose diversity is fostered through data and feature subsampling, the resulting random forest…

OPTIMUS-Prime: Minimal and Sufficient Concept Explanations for Deep Vision Models

2026-06-05 · Arthur Hoarau, Chenrui Zhu, Vu Linh Nguyen arxiv

The growing demand for transparency in automated decision-making has propelled eXplainable Artificial Intelligence (XAI) to the forefront of machine learning research. In computer vision, however, existing explanation me…

Prime Implicates and Prime Implicants: From Propositional to Modal Logic

2014-01-15 · Meghyn Bienvenu

Prime implicates and prime implicants have proven relevant to a number of areas of artificial intelligence, most notably abductive reasoning and knowledge compilation. The purpose of this paper is to examine how these no…