Abstract

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.

Keywords

Computer scienceFlexibility (engineering)Black boxArtificial intelligenceMachine learningTheoretical computer scienceAlgorithmMathematics

Affiliated Institutions

Related Publications

Publication Info

Year
2018
Type
article
Volume
32
Issue
1
Citations
1932
Access
Closed

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1932
OpenAlex
224
Influential
1124
CrossRef

Cite This

Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin (2018). Anchors: High-Precision Model-Agnostic Explanations. Proceedings of the AAAI Conference on Artificial Intelligence , 32 (1) . https://doi.org/10.1609/aaai.v32i1.11491

Identifiers

DOI
10.1609/aaai.v32i1.11491

Data Quality

Data completeness: 81%