Factual and Counterfactual Explanations for Black Box Decision Making

By Riccardo Guidotti, Anna Monreale, Fosca Giannotti, Dino Pedreschi, Salvatore Ruggieri, Franco Turini. 2019

308 citations recorded by the source corpus.

The rise of sophisticated machine learning models has brought accurate but obscure decision systems, which hide their logic, thus undermining transparency, trust, and the adoption of artificial intelligence (AI) in socially sensitive and safety-critical contexts. We introduce a local rule-based explanation method, providing faithful explanations of the decision made by a black box classifier on a specific instance. The proposed method first learns an interpretable, local classifier on a synthetic neighborhood of the instance under investigation, generated by a genetic algorithm. Then, it derives from the interpretable classifier an explanation consisting of a decision rule, explaining the factual reasons of the decision, and a set of counterfactuals, suggesting the changes in the instance features that would lead to a different outcome. Experimental results show that the proposed method outperforms existing approaches in terms of the quality of the explanations and of the accuracy in mimicking the black box.

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

Computing Optimal Decision Sets with SAT (2020, background): “Hence the rising interest in explainable artificial intelligence (XAI) [4, 14, 16, 18, 22, 23, 26, 29, 30, 36–38, 42, 43, 48, 49, 52], including research programs [3, 24] and legislation [17, 21].”
Deterministic Local Interpretable Model-Agnostic Explanations for Stable Explainability (2021, unknown): “In the same vein, Leave-One-Covariate-Out (LOCO) [12] and Local Rule-based Explanation (LORE) [13] are other popular techniques for generating local explanation models that offer local variable importance measures.”
Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation (2023, background): “, attribution methods [61], counterfactual studies [62], simplified model surrogates [63]) or the hybridization of explanations expressed in different modalities, such as visual and textual (e.”
A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021, background): “In contrast to the model-speciﬁc frameworks operating on decision tree output, Guidotti et al. employ decision trees as part of reconstructing the reasoning behind any arbitrary classiﬁer in a post-hoc fashion [140].”