Counterfactual Explanations for Machine Learning: A Review

By Sahil Verma, John P. Dickerson, Keegan E. Hines. 2020

473 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): “See Karimi et al. (2020), Sokol and Flach (2019), Verma et al. (2020) for recent surveys on counterfactual explanations.”
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review (2020, unknown): “For this updated (second) version of the paper, we collected papers that cited the first paper that proposed CFEs for ML, i.e., Wachter et al. [346] and the first version of this CFE survey paper [335].”
Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics (2021, background): “The machine learning explainability has been reviewed thoroughly in recent years [10,14,17,23,28,31,32].”
Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyond (2021, background): “Detailed reviews on counterfactual explanations can be found in [12, 167, 173].”
Towards Robust and Reliable Algorithmic Recourse (2021, background): “These approaches can be broadly characterized along the following dimensions [29]: the level of access they require to the underlying predictive model (black box vs.”
Explaining by Removing: A Unified Framework for Model Explanation (2020, background): “Some prior work applies a different form of counterfactual reasoning to model explanation (Verma et al., 2020).”
Deep Neural Networks and Tabular Data: A Survey (2021, background): “5) Interpretability: Going forward, counterfactual explanations for deep tabular learning can be used to improve the perceived fairness in human–artiﬁcial intelligence (AI) interaction scenarios and to enable personalized decision-making [188].”
Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing (2021, background): “It complements other explainable AI (XAI) surveys and critical retrospectives that focus on definitions, methods, and/or evaluation [33, 15, 77, 1, 103, 51, 42, 133, 26, 44, 82, 121, 12, 86, 54, 19], but not on datasets.”
Benchmarking and survey of explanation methods for black box models (2021, background): “To better understand the complex context and the many available possibilities, we refer the interested reader to [15,120,25].”
Teach Me to Explain: A Review of Datasets for Explainable NLP (2021, background): “The broader machine learning community has championed contrastive explanations that justify why an event occurred or an action was taken instead of some other event or action (Dhurandhar et al., 2018; Miller, 2019; Verma et al., 2020).”