Counterfactual Explanations of Machine Learning Predictions: Opportunities and Challenges for AI Safety

By Kacper Sokol, Peter A. Flach. 2019

94 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Mathematical optimization in classification and regression trees (2021, background): “…Justice (Ridgeway 2013; Zeng et al. 2017), Cybersecurity (Kaloudi and Li 2020; Martínez Torres et al. 2019), Health Care (Bertsimas et al. 2016; Souillard-Mandar et al. 2016), Policy Making (Kleinberg et al. 2018; Wager and Athey 2018), Process Monitoring (Apsemidis et al. 2020), Regulatory…”
Explainable machine learning in deployment (2019, background): “Preece [47] and Sokol and Flach [57] discuss how explainability could compromise on”
A survey of algorithmic recourse: definitions, formulations, solutions, and prospects (2020, background): “Related to recourse, and of practical concern [21, 161, 165, 171], is a study of the ability of an adversary with access to a recourse API in extracting a model.”
A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021, background): “For instance, their use is expected to be safe (revealing model’s internals through counterfactuals may lead to model stealing) [54], fair (discriminatory explanations should be avoided) [55], action-able (suggested changes in the input should be feasible) [56], and accountable (ensuring…”
A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C (2019, methodology): “For this paper, we focus on the increasingly popular notion of “counterfactual” explanations (Martens and Provost 2014; Provost 2014; Chen et al. 2017;Wachter et al. 2018; Nguyen 2018; Sokol and Flach 2019).”