CoChat

Explainable AI: A Review of Machine Learning Interpretability Methods

Open access

The DOI matches its Crossref record; 170 of the 170 references it cites were found in a registry or an index.

Abstract

Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption, with machine learning systems demonstrating superhuman performance in a significant number of tasks. However, this surge in performance, has often been achieved through increased model complexity, turning such systems into “black box” approaches and causing uncertainty regarding the way they operate and, ultimately, the way that they come to decisions. This ambiguity has made it problematic for machine learning systems to be adopted in sensitive yet critical domains, where their value could be immense, such as healthcare. As a result, scientific interest in the field of Explainable Artificial Intelligence (XAI), a field that is concerned with the development of new methods that explain and interpret machine learning models, has been tremendously reignited over recent years. This study focuses on machine learning interpretability methods; more specifically, a literature review and taxonomy of these methods are presented, as well as links to their programming implementations, in the hope that this survey would serve as a reference point for both theorists and practitioners.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/e23010018

Cites

170 of 170 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Google Trends Popularity Index (Max value is 100) of the term “Explainable AI” over the last ten years (2011–2020).
Figure 1 Google Trends Popularity Index (Max value is 100) of the term “Explainable AI” over the last ten years (2011–2020).CC BY · PubMed Central
Figure 2 Taxonomy mind-map of Machine Learning Interpretability Techniques.
Figure 2 Taxonomy mind-map of Machine Learning Interpretability Techniques.CC BY · PubMed Central
Figure 3 Comparison of Interpretability Methods to Explain Deep Learning Models on ImageNet sample images, using the innvestigate package.
Figure 3 Comparison of Interpretability Methods to Explain Deep Learning Models on ImageNet sample images, using the innvestigate package.CC BY · PubMed Central
Figure 4 Local interpretable model-agnostic explanations (LIME) is used to explain the rationale behind the classification of an instance of the Quora Insincere Questions Dataset.
Figure 4 Local interpretable model-agnostic explanations (LIME) is used to explain the rationale behind the classification of an instance of the Quora Insincere Questions Dataset.CC BY · PubMed Central
Figure 5 PDP of a Random Forest model, illustrating the relationship between age (feature) and income percentile (label) using the Census Income dataset (UCI Machine Learning Repository).
Figure 5 PDP of a Random Forest model, illustrating the relationship between age (feature) and income percentile (label) using the Census Income dataset (UCI Machine Learning Repository).CC BY · PubMed Central
Figure 6 Parity testing, using the aequitas library, on the ProPublica COMPAS Recidivism Risk Assessment dataset, with three metrics: False Positive Rate Disparity, False Discovery Rate Disparity, and True Positive Rate Disparity.
Figure 6 Parity testing, using the aequitas library, on the ProPublica COMPAS Recidivism Risk Assessment dataset, with three metrics: False Positive Rate Disparity, False Discovery Rate Disparity, and True Positive Rate Disparity.CC BY · PubMed Central
Figure 7 Comparison of the level of race bias (bias disparity) among different groups in the sample population.
Figure 7 Comparison of the level of race bias (bias disparity) among different groups in the sample population.CC BY · PubMed Central
Figure 8 Fast Gradient Sign Attack (FGSM) on the MNIST dataset. The first row contains unperturbed images, while in the subsequent rows are perturbed using some ϵ value, resulting in the model misclassifying them.
Figure 8 Fast Gradient Sign Attack (FGSM) on the MNIST dataset. The first row contains unperturbed images, while in the subsequent rows are perturbed using some ϵ value, resulting in the model misclassifying them.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

5 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 170 references

Research works printed but not linked: 3

  1. Luss, R., Chen, P.Y., Dhurandhar, A., Sattigeri, P., Zhang, Y., Shanmugam, K., and Tu, C.C. (2019). Generating contrastive explanations with monotonic attribute functions. arXiv.
  2. Van Looveren, A., and Klaise, J. (2019). Interpretable counterfactual explanations guided by prototypes. arXiv.
  3. Wang, X., Jin, H., and He, K. (2019). Natural language adversarial attacks and defenses in word level. arXiv.

Cited by

Items 401–500 of 1,016

Metadata

Authors
Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S.
Affiliations
University of Patras (GR)
Corresponding author
Linardatos, Pantelis
Venue
Entropy
Publisher
MDPI AG
Published
2020-12-25
Volume
23
Issue
1
Pages
18
ISSN
1099-4300 (ISSN-L)
OpenAlex
W3116286104
Cited by
2,922
References
162
Citations by year
2026: 485 · 2025: 702 · 2024: 701 · 2023: 565 · 2022: 370 · 2021: 97 · 2020: 1
FWCI
8.89
Type
journal article
Language
en
Open access
Locations
  • Entropy (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
Keywords
explainable AI, model interpretability, black-box models, medical applications

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.