Anchors: High-Precision Model-Agnostic Explanations

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

Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks

Aditya Chattopadhay , Anirban Sarkar , Prantik Howlader +1 more

Over the last decade, Convolutional Neural Network (CNN) models have been\nhighly successful in solving complex vision problems. However, these deep\nmodels are perceived as "bl...

2018 2018 IEEE Winter Conference on Applic... 2688 citations

On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)

Scott Lundberg , Su‐In Lee

In an industrial maintenance context, degradation diagnosis is the problem of determining the current level of degradation of operating machines based on measurements. With the ...

2024 Dagstuhl Research Online Publication ... 12892 citations

Deep Learning for Case-Based Reasoning Through Prototypes: A Neural Network That Explains Its Predictions

Oscar Li , Hao Liu , Chaofan Chen +1 more

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability---they are particularly difficult to understand because o...

2018 Proceedings of the AAAI Conference on... 390 citations

An Interpretable Model with Globally Consistent Explanations for Credit Risk

Chaofan Chen , Kangcheng Lin , Cynthia Rudin +3 more

We propose a possible solution to a public challenge posed by the Fair Isaac Corporation (FICO), which is to provide an explainable model for credit risk assessment. Rather than...

2018 arXiv (Cornell University) 65 citations

Algorithmic Transparency via Quantitative Input Influence: Theory and Experiments with Learning Systems

Anupam Datta , Shayak Sen , Yair Zick

Algorithmic systems that employ machine learning play an increasing role in making substantive decisions in modern society, ranging from online personalization to insurance and ...

2016 672 citations

Publication Info

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

External Links

Download PDF (Free) View on DOI.org Semantic Scholar

Social Impact

Altmetric

Anchors: High-Precision Model-Agnostic Explanations

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1932

OpenAlex

224

Influential

1124

CrossRef

Cite This

APA Style

                            
                                    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%