{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T03:10:14Z","timestamp":1769742614330,"version":"3.49.0"},"reference-count":70,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T00:00:00Z","timestamp":1648684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-19-PI3A-0004"],"award-info":[{"award-number":["ANR-19-PI3A-0004"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["PRCI grant SLANT"],"award-info":[{"award-number":["PRCI grant SLANT"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EU H2020 ICT 38 call","award":["COALA"],"award-info":[{"award-number":["COALA"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Recent efforts have uncovered various methods for providing explanations that can help interpret the behavior of machine learning programs. Exact explanations with a rigorous logical foundation provide valid and complete explanations, but they have an epistemological problem: they are often too complex for humans to understand and too expensive to compute even with automated reasoning methods. Interpretability requires good explanations that humans can grasp and can compute. We take an important step toward specifying what good explanations are by analyzing the epistemically accessible and pragmatic aspects of explanations. We characterize sufficiently good, or fair and adequate, explanations in terms of counterfactuals and what we call the conundra of the explainee, the agent that requested the explanation. We provide a correspondence between logical and mathematical formulations for counterfactuals to examine the partiality of counterfactual explanations that can hide biases; we define fair and adequate explanations in such a setting. We provide formal results about the algorithmic complexity of fair and adequate explanations. We then detail two sophisticated counterfactual models, one based on causal graphs, and one based on transport theories. We show transport based models have several theoretical advantages over the competition as explanation frameworks for machine learning algorithms.<\/jats:p>","DOI":"10.3390\/make4020014","type":"journal-article","created":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T21:34:29Z","timestamp":1648762469000},"page":"316-349","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Counterfactual Models for Fair and Adequate Explanations"],"prefix":"10.3390","volume":"4","author":[{"given":"Nicholas","family":"Asher","sequence":"first","affiliation":[{"name":"Institut de Recherche en Informatique de Toulouse, Universit\u00e9 Paul Sabatier, 31062 Toulouse, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lucas","family":"De Lara","sequence":"additional","affiliation":[{"name":"Institut de Math\u00e9matiques de Toulouse, Universit\u00e9 Paul Sabatier, 31062 Toulouse, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soumya","family":"Paul","sequence":"additional","affiliation":[{"name":"Telindus, 18 rue du Puits Romain, L-8070 Luxembourg, Luxembourg"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris","family":"Russell","sequence":"additional","affiliation":[{"name":"Amazon Research, 72072 T\u00fcbingen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2018, January 2\u20137). Anchors: High-Precision Model-Agnostic Explanations. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"ref_3","first-page":"841","article-title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GPDR","volume":"31","author":"Wachter","year":"2017","journal-title":"Harv. JL Tech."},{"key":"ref_4","unstructured":"Ignatiev, A., Narodytska, N., and Marques-Silva, J. (2019). On Relating Explanations and Adversarial Examples. Advances in Neural Information Processing Systems, NeurIPS."},{"key":"ref_5","unstructured":"Bachoc, F., Gamboa, F., Halford, M., Loubes, J.M., and Risser, L. (2018). Entropic Variable Projection for Explainability and Intepretability. arXiv."},{"key":"ref_6","unstructured":"Rathi, S. (2019). Generating counterfactual and contrastive explanations using SHAP. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"22071","DOI":"10.1073\/pnas.1900654116","article-title":"Definitions, methods, and applications in interpretable machine learning","volume":"116","author":"Murdoch","year":"2019","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_8","unstructured":"Simonyan, K., Vedaldi, A., and Zisserman, A. (2013). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv."},{"key":"ref_9","unstructured":"Kusner, M.J., Loftus, J., Russell, C., and Silva, R. (2017). Counterfactual fairness. Advances in Neural Information Processing Systems, NeurIPS."},{"key":"ref_10","unstructured":"Butler, R. (1962). An Approach to Explanation. Analytical Philsophy, Oxford University Press."},{"key":"ref_11","unstructured":"Achinstein, P. (1980). The Nature of Explanation, Oxford University Press."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","article-title":"Explanation in artificial intelligence: Insights from the social sciences","volume":"267","author":"Miller","year":"2019","journal-title":"Artif. Intell."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13218-020-00636-z","article-title":"Measuring the quality of explanations: The system causability scale (SCS)","volume":"34","author":"Holzinger","year":"2020","journal-title":"KI-K\u00fcnstliche Intell."},{"key":"ref_14","unstructured":"Verma, S., Dickerson, J., and Hines, K. (2020). Counterfactual explanations for machine learning: A review. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Asher, N., Paul, S., and Russell, C. (2021). Fair and Adequate Explanations. International Cross-Domain Conference for Machine Learning and Knowledge Extraction, Springer.","DOI":"10.1007\/978-3-030-84060-0_6"},{"key":"ref_16","unstructured":"Lewis, D. (1973). Counterfactuals, Basil Blackwell."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Younes, L. (2018). Diffeomorphic Learning. arXiv.","DOI":"10.1007\/978-3-662-58496-5_10"},{"key":"ref_18","unstructured":"Cuturi, M. (2013, January 5\u201310). Sinkhorn distances: Lightspeed computation of optimal transport. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_19","unstructured":"Kurakin, A., Goodfellow, I., and Bengio, S. (2016). Adversarial examples in the physical world. arXiv."},{"key":"ref_20","unstructured":"Dube, S. (2018). High dimensional spaces, deep learning and adversarial examples. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1561\/2200000073","article-title":"Computational Optimal Transport: With Applications to Data Science","volume":"11","author":"Cuturi","year":"2019","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Serrurier, M., Mamalet, F., Gonz\u00e1lez-Sanz, A., Boissin, T., Loubes, J.M., and del Barrio, E. (2021, January 20\u201325). Achieving robustness in classification using optimal transport with hinge regularization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00057"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Fan, X., and Toni, F. (2015, January 25\u201330). On Computing Explanations in Argumentation. Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, TX, USA.","DOI":"10.1609\/aaai.v29i1.9420"},{"key":"ref_24","unstructured":"Ignatiev, A., Narodytska, N., and Marques-Silva, J. (2019). On validating, repairing and refining heuristic ML explanations. arXiv."},{"key":"ref_25","first-page":"90","article-title":"A taxonomy for generating explanations in recommender systems","volume":"32","author":"Friedrich","year":"2011","journal-title":"AI Mag."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Bach, S., Binder, A., Montavon, G., Klauschen, F., M\u00fcller, K.R., and Samek, W. (2015). On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Nam, W.J., Gur, S., Choi, J., Wolf, L., and Lee, S.W. (2020, January 2\u20139). Relative attributing propagation: Interpreting the comparative contributions of individual units in deep neural networks. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v34i03.5632"},{"key":"ref_28","unstructured":"Hempel, C.G. (1965). Aspects of Scientific Explanation, Free Press."},{"key":"ref_29","unstructured":"Ignatiev, A., Narodytska, N., Asher, N., and Marques-Silva, J. (2020). On Relating \u201cWhy?\u201d and \u201cWhy Not?\u201d Explanations. arXiv."},{"key":"ref_30","unstructured":"Molnar, C. (2020, March 12). Interpretable Machine Learning. Lulu. com. Available online: http:\/\/leanpub.com\/interpretable-machine-learning2019."},{"key":"ref_31","unstructured":"Doshi-Velez, F., and Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"556","DOI":"10.2307\/2025310","article-title":"Causation","volume":"70","author":"Lewis","year":"1973","journal-title":"J. Philos."},{"key":"ref_33","unstructured":"Vardi, M.Y. (1988, January 7\u20139). Revisions of Knowledge Systems Using Epistemic Entrenchment. Proceedings of the Second Conference on Theoretical Aspects of Reasoning about Knowledge, Pacific Grove, CA, USA."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1305\/ndjfl\/1093638012","article-title":"First-order logics for comparative similarity","volume":"29","author":"Williamson","year":"1988","journal-title":"Notre Dame J. Form. Log."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Salzberg, S. (1991). Distance metrics for instance-based learning. International Symposium on Methodologies for Intelligent Systems, Springer.","DOI":"10.1007\/3-540-54563-8_103"},{"key":"ref_36","unstructured":"Ignatiev, A., Narodytska, N., and Marques-Silva, J. (February, January 27). Abduction-based explanations for machine learning models. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA."},{"key":"ref_37","unstructured":"Karimi, A.H., Barthe, G., Balle, B., and Valera, I. (2020, January 26\u201328). Model-agnostic counterfactual explanations for consequential decisions. Proceedings of the International Conference on Artificial Intelligence and Statistics, Sicily, Italy."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Laugel, T., Lesot, M.J., Marsala, C., Renard, X., and Detyniecki, M. (2019, January 16\u201320). Unjustified classification regions and counterfactual explanations in machine learning. Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, W\u00fcrzburg, Germany.","DOI":"10.1007\/978-3-030-46147-8_3"},{"key":"ref_39","unstructured":"Lundberg, S.M., and Lee, S. (2017, January 4\u20137). A Unified Approach to Interpreting Model Predictions. Proceedings of the Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_40","unstructured":"Chang, C.C., and Keisler, H.J. (1990). Model Theory, Elsevier."},{"key":"ref_41","unstructured":"Junker, U. (2004, January 25\u201329). Preferred explanations and relaxations for over-constrained problems. Proceedings of the Nineteenth National Conference on Artificial Intelligence, San Jose, CA, USA."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Slack, D., Hilgard, S., Jia, E., Singh, S., and Lakkaraju, H. (2020, January 7\u20138). Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods. Proceedings of the AIES \u201920: AAAI\/ACM Conference on AI, Ethics, and Society, New York, NY, USA.","DOI":"10.1145\/3375627.3375830"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/0004-3702(86)90067-6","article-title":"Counterfactuals","volume":"30","author":"Ginsberg","year":"1986","journal-title":"Artif. Intell."},{"key":"ref_44","unstructured":"Pearl, J. (1990, January 25\u201327). System Z: A natural ordering of defaults with tractable applications to nonmonotonic reasoning. Proceedings of the 3rd Conference on Theoretical Aspects of Reasoning about Knowledge (TARK\u201990), Beijing, China."},{"key":"ref_45","first-page":"355","article-title":"Job Market Signaling","volume":"87","author":"Spence","year":"1973","journal-title":"J. Econ."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/0022-0000(88)90046-3","article-title":"How easy is local search?","volume":"37","author":"Johnson","year":"1988","journal-title":"J. Comput. Syst. Sci."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Papadimitriou, C.H., Sch\u00e4ffer, A.A., and Yannakakis, M. (1990, January 13\u201317). On the complexity of local search. Proceedings of the Twenty-Second Annual ACM Symposium on Theory of Computing, Baltimore, MD, USA.","DOI":"10.1145\/100216.100274"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s10849-018-9271-9","article-title":"Strategic conversation under imperfect information: Epistemic Message Exchange games","volume":"27","author":"Asher","year":"2018","journal-title":"Logic Lang. Inf."},{"key":"ref_49","unstructured":"Alvarez-Melis, D., and Jaakkola, T.S. (2018). On the robustness of interpretability methods. arXiv."},{"key":"ref_50","unstructured":"De Lara, L., Gonz\u00e1lez-Sanz, A., Asher, N., Risser, L., and Loubes, J.M. (2021). Transport-based Counterfactual Models. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/0004-3702(90)90019-V","article-title":"An analysis of first-order logics of probability","volume":"46","author":"Halpern","year":"1990","journal-title":"Artif. Intell."},{"key":"ref_52","unstructured":"Bacchus, F.I. (1989). Representing and Reasoning with Probabilistic Knowledge, MIT Press."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1145\/174652.174658","article-title":"Reasoning about knowledge and probability","volume":"41","author":"Fagin","year":"1994","journal-title":"J. ACM (JACM)"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1006\/inco.1994.1049","article-title":"Decidability and expressiveness for first-order logics of probability","volume":"112","author":"Abadi","year":"1994","journal-title":"Inf. Comput."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Spirtes, P., Glymour, C.N., Scheines, R., and Heckerman, D. (2000). Causation, Prediction, and Search, MIT Press.","DOI":"10.7551\/mitpress\/1754.001.0001"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Pearl, J. (2009). Causality, Cambridge University Press.","DOI":"10.1017\/CBO9780511803161"},{"key":"ref_57","first-page":"351","article-title":"The Computational Complexity of Understanding Binary Classifier Decisions","volume":"70","author":"MacDonald","year":"2021","journal-title":"J. Artif. Intell. Res."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/s00454-016-9757-7","article-title":"Discrete optimal transport: Complexity, geometry and applications","volume":"55","author":"Oudet","year":"2016","journal-title":"Discret. Comput. Geom."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Black, E., Yeom, S., and Fredrikson, M. (2020, January 27\u201330). FlipTest: Fairness Testing via Optimal Transport. Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, Barcelona, Spain.","DOI":"10.1145\/3351095.3372845"},{"key":"ref_60","first-page":"1367","article-title":"Computational optimal transport: Complexity by accelerated gradient descent is better than by Sinkhorn\u2019s algorithm","volume":"26","author":"Dvurechensky","year":"2018","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref_61","unstructured":"Genevay, A., Chizat, L., Bach, F., Cuturi, M., and Peyr\u00e9, G. (2019, January 16\u201318). Sample complexity of sinkhorn divergences. Proceedings of the International Conference on Artificial Intelligence and Statistics, Naha-shi, Japan."},{"key":"ref_62","unstructured":"Pooladian, A.A., and Niles-Weed, J. (2021). Entropic estimation of optimal transport maps. arXiv."},{"key":"ref_63","unstructured":"Seguy, V., Damodaran, B.B., Flamary, R., Courty, N., Rolet, A., and Blondel, M. (2017). Large-scale optimal transport and mapping estimation. arXiv."},{"key":"ref_64","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6\u201311). Wasserstein generative adversarial networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Salmon, W.C. (1984). Scientific Explanation and the Causal Structure of the World, Princeton University Press.","DOI":"10.1515\/9780691221489"},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"De Raedt, L., Duman\u010di\u0107, S., Manhaeve, R., and Marra, G. (2020). From statistical relational to neuro-symbolic artificial intelligence. arXiv.","DOI":"10.24963\/ijcai.2020\/688"},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Poole, D. (2011, January 16\u201319). Logic, probability and computation: Foundations and issues of statistical relational AI. Proceedings of the International Conference on Logic Programming and Nonmonotonic Reasoning, Vancouver, BC, Canada.","DOI":"10.1007\/978-3-642-20895-9_1"},{"key":"ref_68","first-page":"105","article-title":"Power to the people: The role of humans in interactive machine learning","volume":"35","author":"Amershi","year":"2014","journal-title":"Ai Mag."},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"2401","DOI":"10.1007\/s10489-018-1361-5","article-title":"Interactive machine learning: Experimental evidence for the human in the algorithmic loop","volume":"49","author":"Holzinger","year":"2019","journal-title":"Appl. Intell."},{"key":"ref_70","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.inffus.2021.01.008","article-title":"Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI","volume":"71","author":"Holzinger","year":"2021","journal-title":"Inf. Fusion"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/4\/2\/14\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:47:48Z","timestamp":1760136468000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/4\/2\/14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,31]]},"references-count":70,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,6]]}},"alternative-id":["make4020014"],"URL":"https:\/\/doi.org\/10.3390\/make4020014","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,31]]}}}