CoChat
Sign Up
Cited by 271Explainable Artificial Intelligence (XAI)Software Testing and Debugging TechniquesEthics and Social Impacts of AI

Multi-Objective Counterfactual Explanations

Open access
Dandl, Susanne, Molnar, Christoph, Binder, Martin, Bischl, Bernd·2020·Lecture Notes in Computer Science
DOI 10.1007/978-3-030-58112-1_31
Open this paper in CoChat — free accountOpen PDF

Abstract

Counterfactual explanations are one of the most popular methods to make predictions of black box machine learning models interpretable by providing explanations in the form of ‘what-if scenarios’. Most current approaches optimize a collapsed, weighted sum of multiple objectives, which are naturally difficult to balance a-priori. We propose the Multi-Objective Counterfactuals (MOC) method, which translates the counterfactual search into a multi-objective optimization problem. Our approach not only returns a diverse set of counterfactuals with different trade-offs between the proposed objectives, but also maintains diversity in feature space. This enables a more detailed post-hoc analysis to facilitate better understanding and also more options for actionable user responses to change the predicted outcome. Our approach is also model-agnostic and works for numerical and categorical input features. We show the usefulness of MOC in concrete cases and compare our approach with state-of-the-art methods for counterfactual explanations.

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 · 10.1007/978-3-030-58112-1_31

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

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

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?

  • Most methods generate counterfactuals heuristically and therefore produce close rather than closest counterfactuals.

    “While the original formulation of counterfactuals byWachter, Mittelstadt, and Russell (2017) requires the counterfactual to be the closest input across the decision boundary, most methods generate counterfactuals heuristically, e.g. using evolutionary algorithms(Dandl et al. 2020), and therefore produce close rather than closest counterfactuals.”

    From Explainable AI Isn't Enough! Rethinking Algorithmic Contestability (2026) · cites this paper as Dandl et al. 2020

    Section 4.2, “Counterfactual Search” (page unavailable), confirms that Dandl et al. use an evolutionary algorithm to generate counterfactuals, supporting the cited example. The paper does not establish that most methods are heuristic or explicitly conclude that they produce close rather than closest counterfactuals. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

Self-check

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

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

Cites

Flagged first, then by citations

Research works printed but not linked: 30

  1. Avila, S.L., Krähenbühl, L., Sareni, B.: A multi-niching multi-objective genetic algorithm for solving complex multimodal problems. In: OIPE. Sorrento, Italy (2006). https://hal.archives-ouvertes.fr/hal-00398660
  2. Bischl, B., et al.: mlr: Machine Learning in R. J. Mach. Learn. Res. 17(170), 1-5 (2016). http://jmlr.org/papers/v17/15-066.html, R package version 2.17
  3. Breiman, L.: Statistical modeling: the two cultures. Stat. Sci. 16(3), 199-231 (2001). https://doi.org/10.1214/ss/1009213726 · DOI · Paper page
  4. Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182-197 (2002). https://doi.org/10.1109/4235.996017 · DOI · Paper page
  5. Dhurandhar, A., Pedapati, T., Balakrishnan, A., Chen, P., Shanmugam, K., Puri, R.: Model Agnostic Contrastive Explanations for Structured Data. CoRR abs/1906.00117 (2019). http://arxiv.org/abs/1906.00117 · arXiv
  6. Goldstein, A., Kapelner, A., Bleich, J., Pitkin, E.: Peeking inside the black box: visualizing statistical learning with plots of individual conditional expectation. J. Comput. Graph. Stat. 24(1), 44-65 (2015). https://doi.org/10.1080/10618600. 2014.907095 · DOI · Paper page
  7. Gower, J.C.: A general coefficient of similarity and some of its properties. Biomet- rics 27(4), 857-871 (1971)
  8. Grath, R.M., et al.: Interpretable Credit Application Predictions With Counter- factual Explanations. CoRR (abs/1811.05245) (2018). http://arxiv.org/abs/1811. 05245 · arXiv
  9. Greenwell, B.M., Boehmke, B.C., McCarthy, A.J.: A simple and effective model- based variable importance measure. arXiv preprint arXiv:1805.04755 (2018) · arXiv
  10. Joshi, S., Koyejo, O., Vijitbenjaronk, W., Kim, B., Ghosh, J.: Towards Realistic Individual Recourse and Actionable Explanations in black-box decision making systems. CoRR abs/1907.09615 (2019). http://arxiv.org/abs/1907.09615 · arXiv
  11. Karimi, A., Barthe, G., Balle, B., Valera, I.: Model-Agnostic Counterfactual Expla- nations for Consequential Decisions. CoRR (abs/1905.11190) (2019). http://arxiv. org/abs/1905.11190 · arXiv
  12. Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, December 2014
  13. Laugel, T., Lesot, M.J., Marsala, C., Renard, X., Detyniecki, M.: Comparison- Based Inverse Classification for Interpretability in Machine Learning. CoRR (abs/1712.08443) (2017). http://arxiv.org/abs/1712.08443 · arXiv
  14. Li, R., et al.: Mixed integer evolution strategies for parameter optimization. Evol. Comput. 21(1), 29-64 (2013)
  15. Looveren, A.V., Klaise, J.: Interpretable Counterfactual Explanations Guided by Prototypes. CoRR abs/1907.02584 (2019). http://arxiv.org/abs/1907.02584 · arXiv
  16. López-Ibáñez, M., Dubois-Lacoste, J., Cáceres, L.P., Birattari, M., Stützle, T.: The irace package: iterated racing for automatic algorithm configuration. Oper. Res. Perspect. 3, 43-58 (2016). https://doi.org/10.1016/j.orp.2016.09.002, http:// www.sciencedirect.com/science/article/pii/S2214716015300270, R package version 3.4.1 · DOI · Paper page
  17. Molnar, C., Bischl, B., Casalicchio, G.: iml: an R package for interpretable machine learning. JOSS 3(26), 786 (2018). https://doi.org/10.21105/joss.00786 · DOI
  18. Mothilal, R.K., Sharma, A., Tan, C.: Explaining Machine Learning Classifiers through Diverse Counterfactual explanations. CoRR (abs/1905.07697) (2019). http://arxiv.org/abs/1905.07697 · arXiv
  19. Radulescu, A., López-Ibáñez, M., Stützle, T.: Automatically improving the anytime behaviour of multiobjective evolutionary algorithms. In: Purshouse, R.C., Fleming, P.J., Fonseca, C.M., Greco, S., Shaw, J. (eds.) EMO 2013. LNCS, vol. 7811, pp. 825- 840. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-37140-0 61 · DOI
  20. Ribeiro, M.T., Singh, S., Guestrin, C.: "Why should i trust you?" Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD Interna- tional Conference on Knowledge Discovery and Data Mining, pp. 1135-1144 (2016)
  21. Russell, C.: Efficient Search for Diverse Coherent Explanations. CoRR (abs/1901.04909) (2019). http://arxiv.org/abs/1901.04909 · arXiv
  22. Sharma, S., Henderson, J., Ghosh, J.: CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models. CoRR abs/1905.07857 (2019). http://arxiv.org/abs/1905.07857 · arXiv
  23. Su, J., Vargas, D.V., Sakurai, K.: One pixel attack for fooling deep neural networks. IEEE Trans. Evol. Comput. 23, 828-841 (2017)
  24. Syswerda, G.: Uniform crossover in genetic algorithms. In: Proceedings of the 3rd International Conference on Genetic Algorithms, pp. 2-9. Morgan Kaufmann Pub- lishers Inc., San Francisco (1989)
  25. Tolomei, G., Silvestri, F., Haines, A., Lalmas, M.: Interpretable predictions of tree-based ensembles via actionable feature tweaking. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Min- ing, KDD 2017, pp. 465-474. ACM, New York (2017). https://doi.org/10.1145/ 3097983.3098039 · DOI
  26. Ustun, B., Spangher, A., Liu, Y.: Actionable recourse in linear classification. In: Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* 2019, pp. 10-19. ACM, New York (2019). https://doi.org/10.1145/3287560. 3287566 · DOI · Paper page
  27. Vanschoren, J., van Rijn, J.N., Bischl, B., Torgo, L.: OpenML: networked science in machine learning. SIGKDD Explor. 15(2), 49-60 (2013). https://doi.org/10.1145/ 2641190.2641198 · DOI
  28. Wachter, S., Mittelstadt, B.D., Russell, C.: Counterfactual Explanations with- out Opening the Black Box: Automated Decisions and the GDPR. CoRR (abs/1711.00399) (2017). http://arxiv.org/abs/1711.00399 · arXiv
  29. Wexler, J., Pushkarna, M., Bolukbasi, T., Wattenberg, M., Viégas, F.B., Wilson, J.: The What-If Tool: Interactive Probing of Machine Learning Models. CoRR abs/1907.04135 (2019). http://arxiv.org/abs/1907.04135 · arXiv
  30. Zitzler, E., Thiele, L.: Multiobjective optimization using evolutionary algorithms- a comparative case study. In: Eiben, A.E., Bäck, T., Schoenauer, M., Schwefel, H.- P. (eds.) PPSN 1998. LNCS, vol. 1498, pp. 292-301. Springer, Heidelberg (1998). https://doi.org/10.1007/BFb0056872 · DOI

Cited by

Sorted by citations

Authors
Dandl, S., Molnar, C., Binder, M., & Bischl, B.
Affiliations
Ludwig-Maximilians-Universität München (DE)
Corresponding author
Dandl, Susanne
ORCID
Venue
Lecture Notes in Computer Science
Publisher
Springer International Publishing
Published
2020
Pages
448-469
ISSN
  • 0302-9743 (ISSN-L)
  • 1611-3349
DOI
10.1007/978-3-030-58112-1_31
OpenAlex
W3019132020
Cited by
271
References
1
Citations by year
2026: 27 · 2025: 48 · 2024: 59 · 2023: 55 · 2022: 44 · 2021: 31 · 2020: 7
FWCI
12.92
Type
conference paper
Language
en
Open access
Licence
Locations
  • Lecture notes in computer science (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
Bundesministerium für Bildung und Forschung (01IS18036A)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
Keywords
counterfactual explanations, multi-objective optimization, explainable AI, black-box models, what-if scenarios, model-agnostic explanation, post hoc analysis

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