Defining Locality for Surrogates in Post-hoc Interpretablity

Abstract

Local surrogate models, to approximate the local decision boundary of a black-box classifier, constitute one approach to generate explanations for the rationale behind an individual prediction made by the back-box. This paper highlights the importance of defining the right locality, the neighborhood on which a local surrogate is trained, in order to approximate accurately the local black-box decision boundary. Unfortunately, as shown in this paper, this issue is not only a parameter or sampling distribution challenge and has a major impact on the relevance and quality of the approximation of the local black-box decision boundary and thus on the meaning and accuracy of the generated explanation. To overcome the identified problems, quantified with an adapted measure and procedure, we propose to generate surrogate-based explanations for individual predictions based on a sampling centered on particular place of the decision boundary, relevant for the prediction to be explained, rather than on the prediction itself as it is classically done. We evaluate the novel approach compared to state-of-the-art methods and a straightforward improvement thereof on four UCI datasets.

arXiv commentpresented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden

References in corpus (2)

• Understanding Black-box Predictions via Influence Functions
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Cited by in corpus (11)

• A Survey on the Explainability of Supervised Machine Learning
• Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches
• The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations
• Explainable Artificial Intelligence for Pharmacovigilance: What Features Are Important When Predicting Adverse Outcomes?
• FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency
• LIMEtree: Consistent and Faithful Surrogate Explanations of Multiple Classes
• Explaining Predictions by Approximating the Local Decision Boundary
• LEAFAGE: Example-based and Feature importance-based Explanationsfor Black-box ML models
• Interpretabilité des modèles : état des lieux des méthodes et application à l'assurance
• TrustyAI Explainability Toolkit
• XPROAX-Local explanations for text classification with progressive neighborhood approximation