Inverse Classification for Comparison-based Interpretability in Machine Learning

Abstract

In the context of post-hoc interpretability, this paper addresses the task of explaining the prediction of a classifier, considering the case where no information is available, neither on the classifier itself, nor on the processed data (neither the training nor the test data). It proposes an instance-based approach whose principle consists in determining the minimal changes needed to alter a prediction: given a data point whose classification must be explained, the proposed method consists in identifying a close neighbour classified differently, where the closeness definition integrates a sparsity constraint. This principle is implemented using observation generation in the Growing Spheres algorithm. Experimental results on two datasets illustrate the relevance of the proposed approach that can be used to gain knowledge about the classifier.

preprint

References in corpus (3)

• Generating Visual Explanations
• Using Visual Analytics to Interpret Predictive Machine Learning Models
• Explainable Restricted Boltzmann Machines for Collaborative Filtering

Cited by in corpus (19)

• A Survey on the Explainability of Supervised Machine Learning
• Learning Model-Agnostic Counterfactual Explanations for Tabular Data
• Algorithmic Recourse: from Counterfactual Explanations to Interventions
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data
• On Counterfactual Explanations under Predictive Multiplicity
• Model extraction from counterfactual explanations
• ViCE: Visual Counterfactual Explanations for Machine Learning Models
• Health improvement framework for planning actionable treatment process using surrogate Bayesian model
• VINE: Visualizing Statistical Interactions in Black Box Models
• CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
• CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets
• Explaining Predictions by Approximating the Local Decision Boundary
• Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations
• Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning
• Explaining Black-Box Models through Counterfactuals
• Interpretabilité des modèles : état des lieux des méthodes et application à l'assurance
• MCCE: Monte Carlo sampling of realistic counterfactual explanations
• A Series of Unfortunate Counterfactual Events: the Role of Time in Counterfactual Explanations