A Survey on the Explainability of Supervised Machine Learning

By Nadia Burkart, Marco F. Huber. Journal of Artificial Intelligence Research, 2020

965 citations recorded by the source corpus.

Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or finance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/5fca8bbec714e403fa0f95a56b355c8ca835bcc0

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

Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities (2021, background): “General Towards more formalism [1, 31, 10, 32, 9, 33, 26, 2, 34, 8, 35, 36, 37, 18, 38, 39, 40], [41, 42, 43, 44, 45, 46] ∗ Multidisciplinary research collaborations [47, 35, 18, 48, 49, 50], [45, 51, 42] * Explanations and the nature of user experience and expertise [28, 24, 52, 26, 39, 2], [43, 41”
Globally-Consistent Rule-Based Summary-Explanations for Machine Learning Models: Application to Credit-Risk Evaluation (2019, neutral): “…focus on this research area and refer the reader to survey papers on interpretable and explainable machine learning to other bodies of work (Rudin et al. 2022, Došilović et al. 2018, Guidotti et al. 2018b, Arya et al. 2020, Tjoa and Guan 2020, Roscher et al. 2020, Burkart and Huber 2021).”
A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts (2021, methodology): “Blended models (also called interpretable by design [20]) consist partly of intrinsically transparent, symbolic models, that are integrated in sub-symbolic non-transparent ones.”
Explainable artificial intelligence: an analytical review (2021, methodology): “The ML literature predominantly uses the term “ interpretability ” as opposed to “ explainability, ” but according to Burkart and Huber (2020), interpretability itself is insufficient as it does not cover all possible problems associated with understanding “ black-box ” models.”
Teach Me to Explain: A Review of Datasets for Explainable NLP (2021, background): “, 2019), or a combination of these topics (Lipton, 2018; Doshi-Velez and Kim, 2017; Adadi and Berrada, 2018; Murdoch et al., 2019; Verma et al., 2020; Burkart and Huber, 2021), but not on datasets.”
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2022, methodology): “Those terms, together with explainability and interpretability (and to some extent also intelligibility) are typically used interchangeably [29, 32, 93, 177], although a few distinguish between them [21, 173].”
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.”