Anchors: High-Precision Model-Agnostic Explanations

作者：Marco Túlio Ribeiro, Sameer Kumar Singh, Carlos Guestrin · 发表于：Proceedings of the AAAI Conference on Artificial Intelligence · 年份：2018 · DOI：10.1609/aaai.v32i1.11491 · 被引用次数：2140 · 研究领域：Explainable Artificial Intelligence (XAI)、Data Stream Mining Techniques、Machine Learning and Data Classification

We introduce a novel model-agnostic system that explains the behavior of complex models with high-precision rules called anchors, representing local, "sufficient" conditions for predictions. We propose an algorithm to efficiently compute these explanations for any black-box model with high-probability guarantees. We demonstrate the flexibility of anchors by explaining a myriad of different models for different domains and tasks. In a user study, we show that anchors enable users to predict how a model would behave on unseen instances with less effort and higher precision, as compared to existing linear explanations or no explanations.