{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T03:24:23Z","timestamp":1783653863048,"version":"3.55.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T00:00:00Z","timestamp":1632441600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T00:00:00Z","timestamp":1632441600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["427404493"],"award-info":[{"award-number":["427404493"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Otto-Friedrich-Universit\u00e4t Bamberg"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2022,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In recent research, human-understandable explanations of machine learning models have received a lot of attention. Often explanations are given in form of model simplifications or visualizations. However, as shown in cognitive science as well as in early AI research, concept understanding can also be improved by the alignment of a given instance for a concept with a similar counterexample. Contrasting a given instance with a structurally similar example which does not belong to the concept highlights what characteristics are necessary for concept membership. Such near misses have been proposed by Winston (Learning structural descriptions from examples, 1970) as efficient guidance for learning in relational domains. We introduce an explanation generation algorithm for relational concepts learned with Inductive Logic Programming (<jats:sc>GeNME<\/jats:sc>). The algorithm identifies near miss examples from a given set of instances and ranks these examples by their degree of closeness to a specific positive instance. A modified rule which covers the near miss but not the original instance is given as an explanation. We illustrate<jats:sc>GeNME<\/jats:sc>with the well-known family domain consisting of kinship relations, the visual relational Winston arches domain, and a real-world domain dealing with file management. We also present a psychological experiment comparing human preferences of rule-based, example-based, and near miss explanations in the family and the arches domains.<\/jats:p>","DOI":"10.1007\/s10994-021-06048-w","type":"journal-article","created":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T21:51:09Z","timestamp":1632520269000},"page":"1799-1820","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Generating contrastive explanations for inductive logic programming based on a near miss approach"],"prefix":"10.1007","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0656-5881","authenticated-orcid":false,"given":"Johannes","family":"Rabold","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1891-3572","authenticated-orcid":false,"given":"Michael","family":"Siebers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1301-0326","authenticated-orcid":false,"given":"Ute","family":"Schmid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,24]]},"reference":[{"key":"6048_CR1","doi-asserted-by":"publisher","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","volume":"6","author":"A Adadi","year":"2018","unstructured":"Adadi, A., & Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6, 52138\u201352160.","journal-title":"IEEE Access"},{"issue":"4","key":"6048_CR2","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1007\/s10994-020-05941-0","volume":"110","author":"L Ai","year":"2021","unstructured":"Ai, L., Muggleton, S. H., Hocquette, C., Gromowski, M., & Schmid, U. (2021). Beneficial and harmful explanatory machine learning. Machine Learning, 110(4), 695\u2013721.","journal-title":"Machine Learning"},{"issue":"4","key":"6048_CR3","doi-asserted-by":"publisher","first-page":"2403","DOI":"10.1214\/11-AOAS495","volume":"5","author":"J Bien","year":"2011","unstructured":"Bien, J., Tibshirani, R., et al. (2011). Prototype selection for interpretable classification. The Annals of Applied Statistics, 5(4), 2403\u20132424.","journal-title":"The Annals of Applied Statistics"},{"key":"6048_CR4","unstructured":"Dhurandhar, A., Chen, P.-Y., Luss, R., Tu, C.-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 (pp. 592\u2013603)."},{"key":"6048_CR5","doi-asserted-by":"crossref","unstructured":"Ehsan, U., Harrison, B., Chan, L., & Riedl, M.\u00a0O. (2018). Rationalization: A neural machine translation approach to generating natural language explanations. In Proceedings of the 2018 AAAI\/ACM Conference on AI, Ethics, and Society (pp. 81\u201387). ACM.","DOI":"10.1145\/3278721.3278736"},{"issue":"3","key":"6048_CR6","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1111\/j.1467-9280.1994.tb00652.x","volume":"5","author":"D Gentner","year":"1994","unstructured":"Gentner, D., & Markman, A. B. (1994). Structural alignment in comparison: No difference without similarity. Psychological Science, 5(3), 152\u2013158.","journal-title":"Psychological Science"},{"issue":"2","key":"6048_CR7","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1037\/0022-0663.95.2.393","volume":"95","author":"D Gentner","year":"2003","unstructured":"Gentner, D., Loewenstein, J., & Thompson, L. (2003). Learning and transfer: A general role for analogical encoding. Journal of Educational Psychology, 95(2), 393.","journal-title":"Journal of Educational Psychology"},{"issue":"7626","key":"6048_CR8","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/nature20101","volume":"538","author":"A Graves","year":"2016","unstructured":"Graves, A., Wayne, G., Reynolds, M., Harley, T., Danihelka, I., Grabska-Barwi\u0144ska, A., Colmenarejo, S. G., Grefenstette, E., Ramalho, T., Agapiou, J., et al. (2016). Hybrid computing using a neural network with dynamic external memory. Nature, 538(7626), 471.","journal-title":"Nature"},{"key":"6048_CR9","doi-asserted-by":"crossref","unstructured":"Gurumoorthy, K.\u00a0S., Dhurandhar, A., Cecchi, G., & Aggarwal, C. (2019). Efficient data representation by selecting prototypes with importance weights. In IEEE International Conference on Data Mining (ICDM 2019) (pp. 260\u2013269). IEEE.","DOI":"10.1109\/ICDM.2019.00036"},{"key":"6048_CR10","doi-asserted-by":"crossref","unstructured":"Kazemi, S.\u00a0M., & Poole, D. (2018). RelNN: A deep neural model for relational learning. In Thirty-Second AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v32i1.12111"},{"key":"6048_CR11","unstructured":"Kim, B., Koyejo, O., & Khanna, R. et\u00a0al. (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 (NeurIPS 2016), Barcelona, Spain (pp. 2280\u20132288)."},{"issue":"1","key":"6048_CR12","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1073\/pnas.93.1.438","volume":"93","author":"RD King","year":"1996","unstructured":"King, R. D., Muggleton, S. H., Srinivasan, A., & Sternberg, M. (1996). Structure-activity relationships derived by machine learning: The use of atoms and their bond connectivities to predict mutagenicity by inductive logic programming. Proceedings of the National Academy of Sciences, 93(1), 438\u2013442.","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"6048_CR13","unstructured":"Koller, D., Friedman, N., D\u017eeroski, S., Sutton, C., McCallum, A., Pfeffer, A., Abbeel, P., Wong, M.-F., Heckerman, D., Meek, C., et al. (2007). Introduction to statistical relational learning. MIT Press"},{"key":"6048_CR14","doi-asserted-by":"crossref","unstructured":"Lakkaraju, H., Bach, S.\u00a0H., & Leskovec, J. (2016). Interpretable decision sets: A joint framework for description and prediction. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1675\u20131684). ACM.","DOI":"10.1145\/2939672.2939874"},{"key":"6048_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","volume":"267","author":"T Miller","year":"2019","unstructured":"Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267, 1\u201338. https:\/\/doi.org\/10.1016\/j.artint.2018.07.007","journal-title":"Artificial Intelligence"},{"key":"6048_CR16","doi-asserted-by":"crossref","unstructured":"Molnar, C. (2019). Interpretable Machine Learning. Lulu.com.","DOI":"10.21105\/joss.00786"},{"key":"6048_CR17","first-page":"629","volume":"19\u201320","author":"S Muggleton","year":"1994","unstructured":"Muggleton, S., & De Raedt, L. (1994). Inductive logic programming: Theory and methods. Journal of Logic Programming, Special Issue on 10 Years of Logic Programming, 19\u201320, 629\u2013679.","journal-title":"Journal of Logic Programming, Special Issue on 10 Years of Logic Programming"},{"key":"6048_CR18","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1007\/s10994-018-5707-3","volume":"107","author":"SH Muggleton","year":"2018","unstructured":"Muggleton, S. H., Schmid, U., Zeller, C., Tamaddoni-Nezhad, A., & Besold, T. (2018). Ultra-strong machine learning: Comprehensibility of programs learned with ILP. Machine Learning, 107, 1119\u20131140.","journal-title":"Machine Learning"},{"key":"6048_CR19","doi-asserted-by":"crossref","unstructured":"Nguyen, A.\u00a0T., Kharosekar, A., Krishnan, S., Krishnan, S., Tate, E., Wallace, B.\u00a0C., & Lease, M. (2018). Believe it or not: Designing a human-AI partnership for mixed-initiative fact-checking. In The 31st Annual ACM Symposium on User Interface Software and Technology (pp. 189\u2013199). ACM.","DOI":"10.1145\/3242587.3242666"},{"key":"6048_CR20","unstructured":"Palmer, F. R. (1981). Semantics: A New Outline. Cambridge University Press."},{"key":"6048_CR21","doi-asserted-by":"crossref","unstructured":"Pollock, J. L. (1976). The \u2018possible worlds\u2019 analysis of counterfactuals. Philosophical Studies, 29(6), 469\u2013476.","DOI":"10.1007\/BF00646329"},{"key":"6048_CR22","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.\u00a0T., Singh, S., & Guestrin, C. (2016). Why should I trust you?: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135\u20131144). ACM.","DOI":"10.1145\/2939672.2939778"},{"key":"6048_CR23","unstructured":"Rosch, E. (1979). Principles of categorization. In E. Rosch & B. B. Lloyd (Eds.), Cognition and Categorization (pp. 27\u201348). L. Erlbaum."},{"key":"6048_CR24","unstructured":"Samek, W., Wiegand, T., & M\u00fcller, K.-R. (2017). Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. arXiv preprint arXiv:1708.08296."},{"key":"6048_CR25","doi-asserted-by":"crossref","unstructured":"Schmid, U. (2021). Interactive learning with mutual explanations in relational domains. In S. Muggleton & N. Charter (Eds.), Human-like Machine Intelligence (pp. 337\u2013353). Oxford University Press.","DOI":"10.1093\/oso\/9780198862536.003.0017"},{"issue":"1","key":"6048_CR26","first-page":"57","volume":"3","author":"U Schmid","year":"2003","unstructured":"Schmid, U., Wirth, J., & Polkehn, K. (2003). A closer look at structural similarity in analogical transfer. Cognitive Science Quarterly, 3(1), 57\u201389.","journal-title":"Cognitive Science Quarterly"},{"issue":"1","key":"6048_CR27","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s13218-018-0565-5","volume":"33","author":"M Siebers","year":"2019","unstructured":"Siebers, M., & Schmid, U. (2019). Please delete that! Why should I?\u2014Explaining learned irrelevance classifications of digital objects. KI, 33(1), 35\u201344. https:\/\/doi.org\/10.1007\/s13218-018-0565-5.","journal-title":"KI"},{"key":"6048_CR28","unstructured":"Sterling, L., & Shapiro, E. Y. (1994). The art of Prolog: advanced programming techniques. MIT Press"},{"issue":"1\u20132","key":"6048_CR29","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/BF01531174","volume":"4","author":"ME Stickel","year":"1991","unstructured":"Stickel, M. E. (1991). A Prolog-like inference system for computing minimum-cost abductive explanations in natural-language interpretation. Annals of Mathematics and Artificial Intelligence, 4(1\u20132), 89\u2013105.","journal-title":"Annals of Mathematics and Artificial Intelligence"},{"key":"6048_CR30","doi-asserted-by":"crossref","unstructured":"Tamaki, H., & Sato, T. (1986). OLD resolution with tabulation. ppIn E. Shapiro (Ed.), Third International Conference on Logic Programming (pp. 84\u201398). Heidelberg: Springer.","DOI":"10.1007\/3-540-16492-8_66"},{"issue":"8\u20139","key":"6048_CR31","doi-asserted-by":"publisher","first-page":"1653","DOI":"10.1007\/s10994-019-05821-2","volume":"108","author":"JA Telle","year":"2019","unstructured":"Telle, J. A., Hern\u00e1ndez-Orallo, J., & Ferri, C. (2019). The teaching size: Computable teachers and learners for universal languages. Machine Learning, 108(8\u20139), 1653\u20131675.","journal-title":"Machine Learning"},{"key":"6048_CR32","unstructured":"Thaler, A., & Schmid, U. (2021). Explaining machine learned relational concepts in visual domains\u2014Effects of perceived accuracy on joint performance and trust. In Proceedings of the 43rd Annual Conference of the Cognitive Science Society (CogSci\u20192021). Cognitive Science Society."},{"issue":"4","key":"6048_CR33","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1037\/h0070288","volume":"34","author":"LL Thurstone","year":"1927","unstructured":"Thurstone, L. L. (1927). A law of comparative judgment. Psychological Review, 34(4), 273.","journal-title":"Psychological Review"},{"issue":"2","key":"6048_CR34","first-page":"2018","volume":"31","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. Harvard Journal of Law & Technology, 31(2), 2018.","journal-title":"Harvard Journal of Law & Technology"},{"key":"6048_CR35","unstructured":"Winston, P. H. (1970). Learning structural descriptions from examples. Technical Report MIT\/LCS\/TR-76, MIT"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06048-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-021-06048-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06048-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T03:23:48Z","timestamp":1673321028000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-021-06048-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,24]]},"references-count":35,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["6048"],"URL":"https:\/\/doi.org\/10.1007\/s10994-021-06048-w","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,24]]},"assertion":[{"value":"23 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Part of the work reported in this paper is funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation), project 427404493 (Dare2Del). The authors declare that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}