VINE: Visualizing Statistical Interactions in Black Box Models

Abstract

As machine learning becomes more pervasive, there is an urgent need for interpretable explanations of predictive models. Prior work has developed effective methods for visualizing global model behavior, as well as generating local (instance-specific) explanations. However, relatively little work has addressed regional explanations - how groups of similar instances behave in a complex model, and the related issue of visualizing statistical feature interactions. The lack of utilities available for these analytical needs hinders the development of models that are mission-critical, transparent, and align with social goals. We present VINE (Visual INteraction Effects), a novel algorithm to extract and visualize statistical interaction effects in black box models. We also present a novel evaluation metric for visualizations in the interpretable ML space.

References in corpus (10)

• Towards A Rigorous Science of Interpretable Machine Learning
• Predictive learning via rule ensembles
• Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
• Consistent Individualized Feature Attribution for Tree Ensembles
• Supersparse Linear Integer Models for Optimized Medical Scoring Systems
• How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation
• A Simple and Effective Model-Based Variable Importance Measure
• An Interpretable Model with Globally Consistent Explanations for Credit Risk
• Using Visual Analytics to Interpret Predictive Machine Learning Models
• Inverse Classification for Comparison-based Interpretability in Machine Learning

Cited by in corpus (1)

• Shapley Decomposition of R-Squared in Machine Learning Models