Inverse Classification for Comparison-based Interpretability in Machine Learning

By Thibault Laugel, Marie-Jeanne Lesot, C. Marsala, Xavier Renard, Marcin Detyniecki. 2017

121 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

ViCE: visual counterfactual explanations for machine learning models (2020, background): “It is also worth noticing that the visualization interface can accommodate any other counterfactual generation methods [9, 16, 21, 22].”
A survey of algorithmic recourse: definitions, formulations, solutions, and prospects (2020, background): “For instance, cost-minimizing inverse classification problem [4, 101–103, 105, 118], aim to identify the “minimum required change to a case in order to reclassify it as a member of a different preferred class?” [118].”
FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles (2019, methodology): “Fidelity is commonly used to evaluate XAI methods that are based on approximations of a givenmodel: it is ameasure of the agreement between the original modelM and its approximation M̃: fid(M̃, 𝑋 )= 1 𝑁 𝑁∑︁ 𝑛=1 1 [ 𝑦𝑥 (𝑛) =arg max 𝑦′ M̃(𝑦′ |𝑥 (𝑛) ) ] , (26) where 𝑦𝑥 = arg max𝑦 M(𝑦 | �”
Algorithmic Recourse: from Counterfactual Explanations to Interventions (2020, methodology): “…employ mixed-integer linear program solvers to support mixed numeric/binary data; Poyiadzi et al. (2019) use graph-based shortest path algorithms; Laugel et al. (2017) use a heuristic search procedure by growing spheres around the factual instance; Guidotti et al. (2018) and Sharma et al. (2019)…”
A Survey on the Explainability of Supervised Machine Learning (2020, methodology): “Therefore, Growing Sphere gains useful information about the relevant features and illustrates which concepts the classifier has learned so far (Laugel et al., 2017).”
Questioning the AI: Informing Design Practices for Explainable AI User Experiences (2020, methodology): “We conducted semi-structured interviews with 20 UX and de-sign practitioners recruited from multiple product lines at IBM.”