{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:31:20Z","timestamp":1740123080842,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:00:00Z","timestamp":1704844800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:00:00Z","timestamp":1704844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2024,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Machine learning (ML) applications have automated numerous real-life tasks, improving both private and public life. However, the black-box nature of many state-of-the-art models poses the challenge of model verification; how can one be sure that the algorithm bases its decisions on the proper criteria, or that it does not discriminate against certain minority groups? In this paper we propose a way to generate diverse counterfactual explanations from multilinear models, a broad class which includes Random Forests, as well as Bayesian Networks.<\/jats:p>","DOI":"10.1007\/s10994-023-06411-z","type":"journal-article","created":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T17:02:27Z","timestamp":1704906147000},"page":"1421-1443","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Principled diverse counterfactuals in multilinear models"],"prefix":"10.1007","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4282-5820","authenticated-orcid":false,"given":"Ioannis","family":"Papantonis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vaishak","family":"Belle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,10]]},"reference":[{"key":"6411_CR1","doi-asserted-by":"crossref","unstructured":"Belle, V., & Papantonis, I. (2020). Principles and practice of explainable machine learning. CoRR,abs\/2009.11698.","DOI":"10.3389\/fdata.2021.688969"},{"key":"6411_CR2","doi-asserted-by":"crossref","unstructured":"Binns, R., Van\u00a0Kleek, M., Veale, M., Lyngs, U., Zhao, J., & Shadbolt, N. (2018). \u2019It\u2019s reducing a human being to a percentage\u2019: Perceptions of justice in algorithmic decisions. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, CHI\u201918, Association for Computing Machinery, (pp. 1\u201314), New York, NY, USA.","DOI":"10.1145\/3173574.3173951"},{"key":"6411_CR3","volume-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","author":"CM Bishop","year":"2006","unstructured":"Bishop, C. M. (2006). Pattern Recognition and Machine Learning (Information Science and Statistics). Berlin, Heidelberg: Springer."},{"key":"6411_CR4","unstructured":"Boutilier, C., Friedman, N., Goldszmidt, M., & Koller, D. (1996). Context-specific independence in Bayesian networks. In Proceedings of the Twelfth International Conference on Uncertainty in Artificial Intelligence, UAI\u201996, (pp. 115\u2013123), San Francisco, CA: Morgan Kaufmann Publishers Inc."},{"issue":"2","key":"6411_CR5","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00058655","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123\u2013140.","journal-title":"Machine Learning"},{"issue":"3","key":"6411_CR6","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1145\/136035.136043","volume":"24","author":"RE Bryant","year":"1992","unstructured":"Bryant, R. E. (1992). Symbolic Boolean manipulation with ordered binary-decision diagrams. ACM Computing Surveys, 24(3), 293\u2013318.","journal-title":"ACM Computing Surveys"},{"key":"6411_CR7","unstructured":"Choi, A., Shih, A., Goyanka, A., & Darwiche, A. (2020). On symbolically encoding the behavior of random forests. CoRR,abs\/2007.01493."},{"key":"6411_CR8","first-page":"1771","volume":"12","author":"MJ Choi","year":"2011","unstructured":"Choi, M. J., Tan, V. Y. F., Anandkumar, A., & Willsky, A. S. (2011). Learning latent tree graphical models. Journal of Machine Learning Research, 12, 1771\u20131812.","journal-title":"Journal of Machine Learning Research"},{"key":"6411_CR9","doi-asserted-by":"crossref","unstructured":"Conforti, M., Cornu\u00e9jols, G.\u00a0Z. (2014). Integer programming. In Graduate Texts in Mathematics, (p. 271). Springer: Cham.","DOI":"10.1007\/978-3-319-11008-0"},{"key":"6411_CR10","doi-asserted-by":"crossref","unstructured":"Cui, Z., Chen, W., He, Y., & Chen, Y. (2015). Optimal action extraction for random forests and boosted trees. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (pp. 179\u2013188).","DOI":"10.1145\/2783258.2783281"},{"issue":"3","key":"6411_CR11","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1145\/765568.765570","volume":"50","author":"A Darwiche","year":"2003","unstructured":"Darwiche, A. (2003). A differential approach to inference in Bayesian networks. Journal of the ACM, 50(3), 280\u2013305.","journal-title":"Journal of the ACM"},{"key":"6411_CR12","unstructured":"Deng, H. (2014). Interpreting tree ensembles with in trees. arXiv:1408.5456."},{"issue":"7","key":"6411_CR13","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1016\/S0306-4379(98)00021-0","volume":"23","author":"V Dhar","year":"1998","unstructured":"Dhar, V. (1998). Data mining in finance: Using counterfactuals to generate knowledge from organizational information systems. Information Systems, 23(7), 423\u2013437.","journal-title":"Information Systems"},{"issue":"8","key":"6411_CR14","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1016\/j.tips.2019.06.005","volume":"40","author":"\u00d3 D\u00edaz","year":"2019","unstructured":"D\u00edaz, \u00d3., Dalton, J. A., & Giraldo, J. (2019). Artificial intelligence: A novel approach for drug discovery. Trends in Pharmacological Sciences, 40(8), 550\u2013551.","journal-title":"Trends in Pharmacological Sciences"},{"key":"6411_CR15","doi-asserted-by":"crossref","unstructured":"Dressel, J. & Farid, H. (2018). The accuracy, fairness, and limits of predicting recidivism. Science Advances, 4(1), eaao5580.","DOI":"10.1126\/sciadv.aao5580"},{"issue":"3","key":"6411_CR16","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1016\/j.jimonfin.2009.12.009","volume":"29","author":"R Fatum","year":"2010","unstructured":"Fatum, R., & Hutchison, M. M. (2010). Evaluating foreign exchange market intervention: Self-selection, counterfactuals and average treatment effects. Journal of International Money and Finance, 29(3), 570\u2013584.","journal-title":"Journal of International Money and Finance"},{"key":"6411_CR17","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.inffus.2020.07.001","volume":"63","author":"RR Fern\u00e1ndez","year":"2020","unstructured":"Fern\u00e1ndez, R. R., Mart\u00edn de Diego, I., Ace\u00f1a, V., Fern\u00e1ndez-Isabel, A., & Moguerza, J. M. (2020). Random forest explainability using counterfactual sets. Information Fusion, 63, 196\u2013207.","journal-title":"Information Fusion"},{"key":"6411_CR18","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1023\/A:1007465528199","volume":"29","author":"N Friedman","year":"1997","unstructured":"Friedman, N., Geiger, D., Goldszmidt, M., Provan, G., Langley, P., & Smyth, P. (1997). Bayesian network classifiers. Machine Learning, 29, 131\u2013163.","journal-title":"Machine Learning"},{"key":"6411_CR19","unstructured":"Gens, R. & Domingos, P. (2012). Discriminative learning of sum-product networks. Advances in Neural Information Processing Systems, 25."},{"key":"6411_CR20","doi-asserted-by":"crossref","unstructured":"Kanamori, K., Takagi, T., Kobayashi, K., & Arimura, H. (2020). Dace: Distribution-aware counterfactual explanation by mixed-integer linear optimization. In IJCAI, (pp. 2855\u20132862).","DOI":"10.24963\/ijcai.2020\/395"},{"key":"6411_CR21","doi-asserted-by":"publisher","first-page":"11564","DOI":"10.1609\/aaai.v35i13.17376","volume":"35","author":"K Kanamori","year":"2021","unstructured":"Kanamori, K., Takagi, T., Kobayashi, K., Ike, Y., Uemura, K., & Arimura, H. (2021). Ordered counterfactual explanation by mixed-integer linear optimization. In Proceedings of the AAAI Conference on Artificial Intelligence, 35, 11564\u201311574.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"6411_CR22","unstructured":"Karimi, A. -H., Barthe, G., Balle, B., & Valera, I. (2020). Model-agnostic counterfactual explanations for consequential decisions. In International Conference on Artificial Intelligence and Statistics, (pp. 895\u2013905). PMLR."},{"issue":"3","key":"6411_CR23","first-page":"602","volume":"36","author":"D Lewis","year":"1974","unstructured":"Lewis, D. (1974). Tijdschrift Voor Filosofie. Counterfactuals, 36(3), 602\u2013605.","journal-title":"Counterfactuals"},{"issue":"1","key":"6411_CR24","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1093\/ehjdh\/ztaa017","volume":"2","author":"J Lv","year":"2021","unstructured":"Lv, J., Dong, B., Lei, H., Shi, G., Wang, H., Zhu, F., Wen, C., Zhang, Q., Fu, L., Gu, X., et al. (2021). Artificial intelligence-assisted auscultation in detecting congenital heart disease. European Heart Journal-Digital Health, 2(1), 119\u2013124.","journal-title":"European Heart Journal-Digital Health"},{"key":"6411_CR25","doi-asserted-by":"crossref","unstructured":"Mishler, A., Kennedy, E.\u00a0H., & Chouldechova, A. (2021). Fairness in risk assessment instruments: Post-processing to achieve counterfactual equalized odds. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, (pp. 386\u2013400).","DOI":"10.1145\/3442188.3445902"},{"key":"6411_CR26","doi-asserted-by":"crossref","unstructured":"Mohammadi, K., Karimi, A.-H., Barthe, G., & Valera, I. (2021). Scaling guarantees for nearest counterfactual explanations. In Proceedings of the 2021 AAAI\/ACM Conference on AI, Ethics, and Society, (pp. 177\u2013187).","DOI":"10.1145\/3461702.3462514"},{"key":"6411_CR27","doi-asserted-by":"crossref","unstructured":"Moore\u00a0D.\u00a0H. (1987). Classification and regression trees, by leo breiman, jerome h. friedman, richard a. olshen, and charles j. stone. brooks\/cole publishing, monterey, 1984, 358 pages, \\$27.95. Cytometry, 8(5):534\u2013535.","DOI":"10.1002\/cyto.990080516"},{"key":"6411_CR28","doi-asserted-by":"crossref","unstructured":"Mothilal, R.\u00a0K., Sharma, A., & Tan, C. (2020). Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency. Association for Computing Machinery.","DOI":"10.1145\/3351095.3372850"},{"key":"6411_CR29","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161","volume-title":"Causality: Models, Reasoning & Inference","author":"J Pearl","year":"2009","unstructured":"Pearl, J. (2009). Causality: Models, Reasoning & Inference (2nd ed.). Cambridge: Cambridge University Press.","edition":"2"},{"issue":"7","key":"6411_CR30","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1038\/s42256-020-0197-y","volume":"2","author":"M Prosperi","year":"2020","unstructured":"Prosperi, M., Guo, Y., Sperrin, M., Koopman, J. S., Min, J. S., He, X., Rich, S., Wang, M., Buchan, I. E., & Bian, J. (2020). Causal inference and counterfactual prediction in machine learning for actionable healthcare. Nature Machine Intelligence, 2(7), 369\u2013375.","journal-title":"Nature Machine Intelligence"},{"issue":"3","key":"6411_CR31","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/S0020-7373(87)80053-6","volume":"27","author":"JR Quinlan","year":"1987","unstructured":"Quinlan, J. R. (1987). Simplifying decision trees. International Journal of Man\u2013Machine Studies, 27(3), 221\u2013234.","journal-title":"International Journal of Man\u2013Machine Studies"},{"key":"6411_CR32","unstructured":"Rooshenas, A. & Lowd, D. (2014). Learning sum-product networks with direct and indirect variable interactions. In Proceedings of the 31st International Conference on International Conference on Machine Learning, (vol. 32, ICML\u201914, pp. I-710\u2013I-718). JMLR.org."},{"key":"6411_CR33","volume-title":"Explaining Explanation","author":"D Ruben","year":"1990","unstructured":"Ruben, D. (1990). Explaining Explanation. New York: Routledge."},{"key":"6411_CR34","doi-asserted-by":"crossref","unstructured":"Russell, C. (2019). Efficient search for diverse coherent explanations. In Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* \u201919, (pp. 20\u201328), New York, NY, USA.","DOI":"10.1145\/3287560.3287569"},{"issue":"3","key":"6411_CR35","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1111\/j.1745-9125.2006.00055.x","volume":"44","author":"RJ Sampson","year":"2006","unstructured":"Sampson, R. J., Laub, J. H., & Wimer, C. (2006). Does marriage reduce crime? A counterfactual approach to within-individual causal effects. Criminology, 44(3), 465\u2013508.","journal-title":"Criminology"},{"key":"6411_CR36","doi-asserted-by":"crossref","unstructured":"Shi, W., Shih, A., Darwiche, A., & Choi, A. (2020). On tractable representations of binary neural networks.","DOI":"10.24963\/kr.2020\/91"},{"key":"6411_CR37","doi-asserted-by":"crossref","unstructured":"Shih, A., Choi, A., & Darwiche, A. (2018). A symbolic approach to explaining Bayesian network classifiers. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, International Joint Conferences on Artificial Intelligence Organization, (pp. 5103\u20135111).","DOI":"10.24963\/ijcai.2018\/708"},{"key":"6411_CR38","doi-asserted-by":"crossref","unstructured":"Tolomei, G., Silvestri, F., Haines, A., & Lalmas, M. (2017). Interpretable predictions of tree-based ensembles via actionable feature tweaking. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (pp. 465\u2013474).","DOI":"10.1145\/3097983.3098039"},{"issue":"4","key":"6411_CR39","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.dsx.2020.04.012","volume":"14","author":"R Vaishya","year":"2020","unstructured":"Vaishya, R., Javaid, M., Khan, I. H., & Haleem, A. (2020). Artificial intelligence (AI) applications for Covid-19 pandemic. Diabetes & Metabolic Syndrome: Clinical Research & Reviews, 14(4), 337\u2013339.","journal-title":"Diabetes & Metabolic Syndrome: Clinical Research & Reviews"},{"issue":"3","key":"6411_CR40","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1093\/aje\/kwz198","volume":"189","author":"TJ VanderWeele","year":"2020","unstructured":"VanderWeele, T. J. (2020). Invited commentary: Counterfactuals in social epidemiology-thinking outside of \u201cthe box\u2019\u2019. American Journal of Epidemiology, 189(3), 175\u2013178.","journal-title":"American Journal of Epidemiology"},{"key":"6411_CR41","unstructured":"Verma, S., Boonsanong, V., Hoang, M., Hines, K.\u00a0E., Dickerson, J.\u00a0P., & Shah, C. (2020). Counterfactual explanations and algorithmic recourses for machine learning: A review. arXiv preprint arXiv:2010.10596."},{"key":"6411_CR42","doi-asserted-by":"publisher","first-page":"8512","DOI":"10.1609\/aaai.v36i8.20828","volume":"36","author":"S Verma","year":"2022","unstructured":"Verma, S., Hines, K., & Dickerson, J. P. (2022). Amortized generation of sequential algorithmic recourses for black-box models. In Proceedings of the AAAI Conference on Artificial Intelligence, 36, 8512\u20138519.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"6411_CR43","volume-title":"Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR","author":"S Wachter","year":"2017","unstructured":"Wachter, S., Mittelstadt, B., & Russell, C. (2017). Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR. European Economics: Microeconomics & Industrial Organization eJournal."},{"issue":"1","key":"6411_CR44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13063-020-04976-x","volume":"22","author":"EH Weissler","year":"2021","unstructured":"Weissler, E. H., Naumann, T., Andersson, T., Ranganath, R., Elemento, O., Luo, Y., Freitag, D. F., Benoit, J., Hughes, M. C., Khan, F., et al. (2021). The role of machine learning in clinical research: transforming the future of evidence generation. Trials, 22(1), 1\u201315.","journal-title":"Trials"},{"key":"6411_CR45","unstructured":"Zhao, H., Melibari, M., & Poupart, P. (2015). On the relationship between sum-product networks and Bayesian networks. In Proceedings of the 32nd International Conference on Machine Learning."},{"key":"6411_CR46","unstructured":"Zhao, H., Poupart, P., & Gordon, G.\u00a0J. (2016). A unified approach for learning the parameters of sum-product networks. In Advances in Neural Information Processing Systems."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06411-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06411-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06411-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T23:06:20Z","timestamp":1708988780000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-023-06411-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,10]]},"references-count":46,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["6411"],"URL":"https:\/\/doi.org\/10.1007\/s10994-023-06411-z","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2024,1,10]]},"assertion":[{"value":"2 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The code will be made publicly available online, upon acceptance of this work. .","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}]}}