A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C

By Yanou Ramon, David Martens, Foster J. Provost, Theodoros Evgeniou. 2019

96 citations recorded by the source corpus.

Predictive systems based on high-dimensional behavioral and textual data have serious comprehensibility and transparency issues: linear models require investigating thousands of coefficients, while the opaqueness of nonlinear models makes things worse. Counterfactual explanations are becoming increasingly popular for generating insight into model predictions. This study aligns the recently proposed linear interpretable model-agnostic explainer and Shapley additive explanations with the notion of counterfactual explanations, and empirically compares the effectiveness and efficiency of these novel algorithms against a model-agnostic heuristic search algorithm for finding evidence counterfactuals using 13 behavioral and textual data sets. We show that different search methods have different strengths, and importantly, that there is much room for future research.

Subfields: Artificial Intelligence, Statistics and Probability

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

In Statistics and Probability

Citations in the corpus

Mathematical optimization in classification and regression trees (2021, background): “…et al. 2016; Pospisil and Lee 2019; Rahman et al. 2019), text data (Martens and Provost Mathematical optimization in classification and regression… 2014; Ramon et al. 2020), or network data (Óskarsdóttir et al. 2020), which are not captured appropriately by standard implementations of these models.”
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review (2020, unknown): “(8) Functional data: [50, 183] and Behavioral data: [251].”