Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 471

The DOI matches its Crossref record; 102 of the 102 references it cites were found in a registry or an index.

Counterfactual explanations and how to find them: literature review and benchmarking

Open access
Guidotti, Riccardo·2024·Data Mining and Knowledge Discovery

Abstract

Interpretable machine learning aims at unveiling the reasons behind predictions returned by uninterpretable classifiers. One of the most valuable types of explanation consists of counterfactuals. A counterfactual explanation reveals what should have been different in an instance to observe a diverse outcome. For instance, a bank customer asks for a loan that is rejected. The counterfactual explanation consists of what should have been different for the customer in order to have the loan accepted. Recently, there has been an explosion of proposals for counterfactual explainers. The aim of this work is to survey the most recent explainers returning counterfactual explanations. We categorize explainers based on the approach adopted to return the counterfactuals, and we label them according to characteristics of the method and properties of the counterfactuals returned. In addition, we visually compare the explanations, and we report quantitative benchmarking assessing minimality, actionability, stability, diversity, discriminative power, and running time. The results make evident that the current state of the art does not provide a counterfactual explainer able to guarantee all these properties simultaneously.

Overview

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1007/s10618-022-00831-6

Cites

102 of 102 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

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 102 references

Research works printed but not linked: 50

  1. Anjomshoae S, Najjar A, Calvaresi D, Främling K (2019) Explainable agents and robots: results from a systematic literature review. In: Proceedings of the 18th international conference on autonomous agents and multiagent systems, AAMAS’19, Montreal, QC, Canada, May 13–17, 2019, International Foundation for Autonomous Agents and Multiagent Systems, pp 1078–1088
  2. Arrieta AB, Ser JD (2020) Plausible counterfactuals: auditing deep learning classifiers with realistic adversarial examples. In: 2020 International joint conference on neural networks, IJCNN 2020, Glasgow, United Kingdom, July 19–24, 2020, IEEE, pp 1–7
  3. Artelt A, Hammer B (2019) On the computation of counterfactual explanations—a survey. CoRR arXiv:1911.07749 · arXiv
  4. Artelt A, Hammer B (2020b) Efficient computation of counterfactual explanations of LVQ models. In: 28th European symposium on artificial neural networks, computational intelligence and machine learning, ESANN 2020, Bruges, Belgium, October 2–4, 2020, pp 19–24
  5. Balasubramanian R, Sharpe S, Barr B, Wittenbach JD, Bruss CB (2020) Latent-cf: a simple baseline for reverse counterfactual explanations. CoRR arXiv:2012.09301 · arXiv
  6. Ballet V, Renard X, Aigrain J, Laugel T, Frossard P, Detyniecki M (2019) Imperceptible adversarial attacks on tabular data. CoRR arXiv:1911.03274 · arXiv
  7. Bodria F, Giannotti F, Guidotti R, Naretto F, Pedreschi D, Rinzivillo S (2021) Benchmarking and survey of explanation methods for black box models. CoRR arXiv:2102.13076 · arXiv
  8. Brughmans D, Martens D (2021) NICE: an algorithm for nearest instance counterfactual explanations. CoRR arXiv:2104.07411 · arXiv
  9. (ed) Proceedings of the twenty-eighth international joint conference on artificial intelligence, IJCAI 2019, Macao, China, August 10-16, 2019, ijcai.org, pp 6276-6282
  10. Chapman-Rounds M, Schulz M, Pazos E, Georgatzis K (2019) EMAP: explanation by minimal adversarial perturbation. CoRR arXiv:1912.00872 · arXiv
  11. Dhurandhar A, Chen P, Luss R, Tu C, Ting P, Shanmugam K, Das P (2018) Explanations based on the missing: towards contrastive explanations with pertinent negatives. In: Advances in neural information processing systems 31: annual conference on neural information processing systems 2018, NeurIPS 2018, December 3–8, 2018, Montréal, Canada, pp 590–601
  12. Dhurandhar A, Pedapati T, Balakrishnan A, Chen P, Shanmugam K, Puri R (2019) Model agnostic contrastive explanations for structured data. CoRR arXiv:1906.00117 · arXiv
  13. Downs M, Chu JL, Yacoby Y, Doshi-Velez F, Pan W (2020) CRUDS: counterfactual recourse using disentangled subspaces. In: ICML workshop on human interpretability in machine learning
  14. Fan C, Li P (2020) Classification acceleration via merging decision trees. In: FODS’20: ACM-IMS foundations of data science conference, virtual event, USA, October 19–20, 2020, ACM, pp 13–22 · doi:10.1145/3412815.3416886
  15. Fernandez C, Provost FJ, Han X (2020) Explaining data-driven decisions made by AI systems: the counterfactual approach. CoRR arXiv:2001.07417 · arXiv
  16. Goyal Y, Wu Z, Ernst J, Batra D, Parikh D, Lee S (2019) Counterfactual visual explanations. In: Proceedings of the 36th international conference on machine learning, ICML 2019, 9–15 June 2019, Long Beach, California, USA, PMLR, Proceedings of machine learning research, vol 97, pp 2376–2384
  17. Hashemi M, Fathi A (2020) Permuteattack: counterfactual explanation of machine learning credit scorecards. CoRR arXiv:2008.10138 · arXiv
  18. Joshi S, Koyejo O, Vijitbenjaronk W, Kim B, Ghosh J (2019) Towards realistic individual recourse and actionable explanations in black-box decision making systems. CoRR arXiv:1907.09615 · arXiv
  19. Kang S, Jung H, Won D, Lee S (2020) Counterfactual explanation based on gradual construction for deep networks. CoRR arXiv:2008.01897 · arXiv
  20. Karimi A, Barthe G, Balle B, Valera I (2020) Model-agnostic counterfactual explanations for consequential decisions. In: The 23rd international conference on artificial intelligence and statistics, AISTATS 2020, 26–28 August 2020, Online [Palermo, Sicily, Italy], PMLR, Proceedings of machine learning research, vol 108, pp 895–905
  21. Karimi A, Barthe G, Schölkopf B, Valera I (2021a) A survey of algorithmic recourse: definitions, formulations, solutions, and prospects. CoRR arXiv:2010.04050 · arXiv
  22. Kim B, Koyejo O, Khanna R (2016) Examples are not enough, learn to criticize! criticism for interpretability. In: Advances in neural information processing systems 29: annual conference on neural information processing systems 2016, December 5–10, 2016, Barcelona, Spain, pp 2280–2288
  23. Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015, Conference track proceedings
  24. Klys J, Snell J, Zemel RS (2018) Learning latent subspaces in variational autoencoders. In: Advances in neural information processing systems 31: annual conference on neural information processing systems 2018, NeurIPS 2018, December 3–8, 2018, Montréal, Canada, pp 6445–6455
  25. Koh PW, et al. (2017) Understanding black-box predictions via influence functions. In: Proceedings of the 34th international conference on machine learning, ICML 2017, Sydney, NSW, Australia, 6–11 August 2017, PMLR, Proceedings of machine learning research, vol 70, pp 1885–1894
  26. Kusner MJ, Loftus JR, Russell C, Silva R (2017) Advances in neural information processing systems 30: annual conference on neural information processing systems 2017, December 4–9, 2017, long beach, ca, USA. In: NIPS, pp 4066–4076
  27. Lucic A, Oosterhuis H, Haned H, de Rijke M (2019) Focus: flexible optimizable counterfactual explanations for tree ensembles. CoRR arXiv:1911.12199 · arXiv
  28. Lucic A, Ter Hoeve M, Tolomei G, de Rijke M, Silvestri F (2021) Cf-gnnexplainer: counterfactual explanations for graph neural networks. CoRR arXiv:2102.03322 · arXiv
  29. Lundberg SM, Lee S (2017) A unified approach to interpreting model predictions. In: Advances in neural information processing systems 30: annual conference on neural information processing systems 2017, December 4–9, 2017, Long Beach, CA, USA, pp 4765–4774
  30. Mahajan D, Tan C, Sharma A (2019) Preserving causal constraints in counterfactual explanations for machine learning classifiers. CoRR arXiv:1912.03277 · arXiv
  31. Mc Grath R, Costabello L, Le Van C, Sweeney P, Kamiab F, Shen Z, Lécué F (2018) Interpretable credit application predictions with counterfactual explanations. CoRR arXiv:1811.05245 · arXiv
  32. Miller T (2018) Contrastive explanation: a structural-model approach. CoRR arXiv:1811.03163 · arXiv
  33. Parmentier A, Vidal T (2021) Optimal counterfactual explanations in tree ensembles. In: Proceedings of the 38th international conference on machine learning, ICML 2021, 18–24 July 2021, Virtual Event, PMLR, Proceedings of machine learning research, vol 139, pp 8422–8431
  34. Pawelczyk M, Bielawski S, van den Heuvel J, Richter T, Kasneci G (2021) CARLA: a python library to benchmark algorithmic recourse and counterfactual explanation algorithms. CoRR arXiv:2108.00783 · arXiv
  35. Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I et al (2019) Language models are unsupervised multitask learners. OpenAI Blog 1(8):9
  36. Rathi S (2019) Generating counterfactual and contrastive explanations using SHAP. CoRR arXiv:1906.09293 · arXiv
  37. Slack D, Hilgard S, Lakkaraju H, Singh S (2021) Counterfactual explanations can be manipulated. Advances in Neural Information Processing Systems 34
  38. Strecht P (2015) A survey of merging decision trees data mining approaches. In: Proceedings of 10th doctoral symposium in informatics engineering, pp 36–47
  39. Tjoa E, Guan C (2019) A survey on explainable artificial intelligence (XAI): towards medical XAI. CoRR arXiv:1907.07374 · arXiv
  40. Tomsett R, Braines D, Harborne D, Preece AD, Chakraborty S (2018) Interpretable to whom? A role-based model for analyzing interpretable machine learning systems. CoRR arXiv:1806.07552 · arXiv
  41. Tsirtsis S, Rodriguez MG (2020) Decisions, counterfactual explanations and strategic behavior. In: NeurIPS
  42. Van Der Waa J, Robeer M, Van Diggelen J, Brinkhuis M, Neerincx MA (2019) Contrastive explanations with local foil trees. CoRR arXiv:1806.07470 · arXiv
  43. Verma S, Dickerson JP, Hines K (2020) Counterfactual explanations for machine learning: a review. CoRR arXiv:2010.10596 · arXiv
  44. Von Kügelgen J, Bhatt U, Karimi A, Valera I, Weller A, Schölkopf B (2020) On the fairness of causal algorithmic recourse. CoRR arXiv:2010.06529 · arXiv
  45. Wachter S, Mittelstadt BD, Russell C (2017) Counterfactual explanations without opening the black box: automated decisions and the GDPR. Harv JL Tech 31:841
  46. Waters A, Miikkulainen R (2014) GRADE: machine learning support for graduate admissions. AI Mag 35(1):64–75
  47. Wexler J, Pushkarna M, Bolukbasi T, Wattenberg M, Viégas FB, Wilson J (2020) The what-if tool: interactive probing of machine learning models. IEEE Trans Vis Comput Graph 26(1):56–65
  48. White A, d’Avila Garcez AS (2020) Measurable counterfactual local explanations for any classifier. In: ECAI 2020—24th European conference on artificial intelligence, 29 August–8 September 2020, Santiago de Compostela, Spain, August 29–September 8, 2020 - Including 10th conference on prestigious applications of artificial intelligence (PAIS 2020), IOS Press, Frontiers in Artificial Intelligence and Applications, vol 325, pp 2529–2535
  49. Zhang X, Solar-Lezama A, Singh R (2018) Interpreting neural network judgments via minimal, stable, and symbolic corrections. In: Advances in neural information processing systems 31: annual conference on neural information processing systems 2018, NeurIPS 2018, December 3–8, 2018, Montréal, Canada, pp 4879–4890
  50. Zhao Y (2020) Fast real-time counterfactual explanations. CoRR arXiv:2007.05684 · arXiv

Cited by

See all 471

Metadata

Authors
Guidotti, R.
Venue
Data Mining and Knowledge Discovery
Published
2022-04-28
Volume
38
Issue
5
Pages
2770-2824
ISSN
  • 1384-5810 (ISSN-L)
  • 1573-756X
OpenAlex
W4225150645
Cited by
471
References
102
FWCI
28.92
Type
journal article
Language
en
Open access
hybrid
Licence
Funders
  • SoBigData++ (871042)
  • HumanE AI Net (952026)
  • XAI (834756)
  • TAILOR (952215)

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Counterfactual explanations and how to find them: literature review and benchmarking. https://app.cochat.ai/papers/10.1007/s10618-022-00831-6
The paper
Guidotti, R. (2024). Counterfactual explanations and how to find them: literature review and benchmarking. Data Mining and Knowledge Discovery. https://doi.org/10.1007/s10618-022-00831-6

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.