{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:06:39Z","timestamp":1770815199961,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,8,22]],"date-time":"2018-08-22T00:00:00Z","timestamp":1534896000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2019,2]]},"DOI":"10.1007\/s10994-018-5746-9","type":"journal-article","created":{"date-parts":[[2018,8,22]],"date-time":"2018-08-22T18:45:20Z","timestamp":1534963520000},"page":"229-266","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["A scalable robust and automatic propositionalization approach for Bayesian classification of large mixed numerical and categorical data"],"prefix":"10.1007","volume":"108","author":[{"given":"Marc","family":"Boull\u00e9","sequence":"first","affiliation":[]},{"given":"Cl\u00e9ment","family":"Charnay","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4318-4252","authenticated-orcid":false,"given":"Nicolas","family":"Lachiche","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,22]]},"reference":[{"issue":"21","key":"5746_CR1","doi-asserted-by":"publisher","first-page":"7698","DOI":"10.1016\/j.eswa.2015.05.053","volume":"42","author":"CF Ahmed","year":"2015","unstructured":"Ahmed, C. F., Lachiche, N., Charnay, C., Jelali, S. E., & Braud, A. (2015). Flexible propositionalization of continuous attributes in relational data mining. Expert Systems with Applications, 42(21), 7698\u20137709. https:\/\/doi.org\/10.1016\/j.eswa.2015.05.053 .","journal-title":"Expert Systems with Applications"},{"key":"5746_CR2","unstructured":"Bache, K., & Lichman, M. (2013). UCI machine learning repository. http:\/\/archive.ics.uci.edu\/ml ."},{"issue":"1\u20132","key":"5746_CR3","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/S0004-3702(98)00034-4","volume":"101","author":"H Blockeel","year":"1998","unstructured":"Blockeel, H., & De Raedt, L. (1998). Top-down induction of first-order logical decision trees. Artificial Intelligence, 101(1\u20132), 285\u2013297.","journal-title":"Artificial Intelligence"},{"key":"5746_CR4","first-page":"1431","volume":"6","author":"M Boull\u00e9","year":"2005","unstructured":"Boull\u00e9, M. (2005). A Bayes optimal approach for partitioning the values of categorical attributes. Journal of Machine Learning Research, 6, 1431\u20131452.","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"5746_CR5","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s10994-006-8364-x","volume":"65","author":"M Boull\u00e9","year":"2006","unstructured":"Boull\u00e9, M. (2006). MODL: A Bayes optimal discretization method for continuous attributes. Machine Learning, 65(1), 131\u2013165.","journal-title":"Machine Learning"},{"key":"5746_CR6","first-page":"1659","volume":"8","author":"M Boull\u00e9","year":"2007","unstructured":"Boull\u00e9, M. (2007). Compression-based averaging of selective naive Bayes classifiers. Journal of Machine Learning Research, 8, 1659\u20131685.","journal-title":"Journal of Machine Learning Research"},{"key":"5746_CR7","first-page":"1367","volume":"10","author":"M Boull\u00e9","year":"2009","unstructured":"Boull\u00e9, M. (2009). A parameter-free classification method for large scale learning. Journal of Machine Learning Research, 10, 1367\u20131385.","journal-title":"Journal of Machine Learning Research"},{"key":"5746_CR8","doi-asserted-by":"publisher","unstructured":"Boull\u00e9, M. (2014). Towards automatic feature construction for supervised classification. In T. Calders, F. Esposito, E. H\u00fcllermeier, & R. Meo (Eds.), Machine learning and knowledge discovery in databases\u2014European conference, ECML PKDD 2014, Nancy, France, September 15\u201319, 2014. Proceedings, Part I, Lecture Notes in Computer Science (Vol. 8724, pp 181\u2013196). Springer. https:\/\/doi.org\/10.1007\/978-3-662-44848-9_12 .","DOI":"10.1007\/978-3-662-44848-9_12"},{"key":"5746_CR9","doi-asserted-by":"publisher","unstructured":"Burke, M. (2013). Multilinear function factorisation for time series feature extraction. In 18th international conference on digital signal processing (DSP) (pp. 1\u20138). IEEE. https:\/\/doi.org\/10.1109\/ICDSP.2013.6622721","DOI":"10.1109\/ICDSP.2013.6622721"},{"key":"5746_CR10","doi-asserted-by":"publisher","unstructured":"Ceci, M., Appice, A., & Malerba, D. (2003). Mr-sbc: A multi-relational na\u00efve bayes classifier. In N. Lavrac, D. Gamberger, H. Blockeel, & L. Todorovski (Eds.), Knowledge discovery in databases: PKDD 2003, 7th European conference on principles and practice of knowledge discovery in databases, Cavtat-Dubrovnik, Croatia, September 22\u201326, 2003, Proceedings, Lecture Notes in Computer Science (Vol. 2838, pp. 95\u2013106). Springer. https:\/\/doi.org\/10.1007\/978-3-540-39804-2_11 .","DOI":"10.1007\/978-3-540-39804-2_11"},{"key":"5746_CR11","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611","volume-title":"Elements of information theory","author":"T Cover","year":"1991","unstructured":"Cover, T., & Thomas, J. (1991). Elements of information theory. New York: Wiley-Interscience."},{"key":"5746_CR12","doi-asserted-by":"crossref","unstructured":"De Raedt, L. (1998). Attribute-value learning versus inductive logic programming: The missing links (extended abstract). In D. Page (Ed.), Proceedings of the 8th international workshop on inductive logic programming, ILP\u201998 (pp. 1\u20138). Springer","DOI":"10.1007\/BFb0027304"},{"key":"5746_CR13","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar, J. (2006). Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Reseasrch, 7, 1\u201330.","journal-title":"Journal of Machine Learning Reseasrch"},{"key":"5746_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04599-2","volume-title":"Relational data mining","author":"S D\u017eeroski","year":"2001","unstructured":"D\u017eeroski, S., & Lavra\u010d, N. (2001). Relational data mining. New York: Springer."},{"issue":"5","key":"5746_CR15","first-page":"363","volume":"12","author":"S D\u017eeroski","year":"1998","unstructured":"D\u017eeroski, S., Schulze-Kremer, S., Heidtke, K. R., Siems, K., Wettschereck, D., & Blockeel, H. (1998). Diterpene structure elucidation from 13C NMR spectra with inductive logic programming. Applied Artificial Intelligence, Special Issue on First-Order Knowledge Discovery in Databases, 12(5), 363\u2013383.","journal-title":"Applied Artificial Intelligence, Special Issue on First-Order Knowledge Discovery in Databases"},{"key":"5746_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-4541-9","volume-title":"An introduction to the bootstrap. Monographs on statistics and applied probability","author":"B Efron","year":"1993","unstructured":"Efron, B., & Tibshirani, R. (1993). An introduction to the bootstrap. Monographs on statistics and applied probability (Vol. 57). New York: Chapman & Hall."},{"key":"5746_CR17","unstructured":"Fawcett, T. (2003). ROC graphs: Notes and practical considerations for researchers. Technical Report HPL-2003-4, HP Laboratories."},{"key":"5746_CR18","doi-asserted-by":"crossref","unstructured":"F\u00e9raud, R., Boull\u00e9, M., Cl\u00e9rot, F., Fessant, F., Lemaire, V. (2010). The orange customer analysis platform. In Proceedings of the 10th industrial conference on data mining (pp. 584\u2013594). Springer.","DOI":"10.1007\/978-3-642-14400-4_45"},{"issue":"3","key":"5746_CR19","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1023\/B:MACH.0000039778.69032.ab","volume":"57","author":"PA Flach","year":"2004","unstructured":"Flach, P. A., & Lachiche, N. (2004). Naive Bayesian classification of structured data. Machine Learning, 57(3), 233\u2013269. https:\/\/doi.org\/10.1023\/B:MACH.0000039778.69032.ab .","journal-title":"Machine Learning"},{"issue":"1","key":"5746_CR20","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s10994-013-5392-1","volume":"94","author":"MVM Fran\u00e7a","year":"2014","unstructured":"Fran\u00e7a, M. V. M., Zaverucha, G., & d\u2019Avila Garcez, A. S. (2014). Fast relational learning using bottom clause propositionalization with artificial neural networks. Machine Learning, 94(1), 81\u2013104. https:\/\/doi.org\/10.1007\/s10994-013-5392-1 .","journal-title":"Machine Learning"},{"issue":"3","key":"5746_CR21","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1023\/B:MACH.0000039777.23772.30","volume":"57","author":"T G\u00e4rtner","year":"2004","unstructured":"G\u00e4rtner, T., Lloyd, J. W., & Flach, P. A. (2004). Kernels and distances for structured data. Machine Learning, 57(3), 205\u2013232. https:\/\/doi.org\/10.1023\/B:MACH.0000039777.23772.30 .","journal-title":"Machine Learning"},{"key":"5746_CR22","volume-title":"Feature extraction: Foundations and applications","year":"2006","unstructured":"Guyon, I., Gunn, S., Nikravesh, M., & Zadeh, L. (Eds.). (2006). Feature extraction: Foundations and applications. Berlin: Springer."},{"key":"5746_CR23","doi-asserted-by":"publisher","unstructured":"Knobbe, A. J., de Haas, M., & Siebes, A. (2001). Propositionalisation and aggregates. In L. D. Raedt, & A. Siebes (Eds.), Principles of data mining and knowledge discovery, 5th European conference, PKDD 2001, Freiburg, Germany, September 3\u20135, 2001, Proceedings, Lecture notes in computer science (Vol. 2168, pp. 277\u2013288). Springer. https:\/\/doi.org\/10.1007\/3-540-44794-6_23 .","DOI":"10.1007\/3-540-44794-6_23"},{"key":"5746_CR24","doi-asserted-by":"publisher","unstructured":"Kramer, S., Pfahringer, B., & Helma, C. (1998). Stochastic propositionalization of non-determinate background knowledge. In D. Page (Ed.) Inductive logic programming, 8th international workshop, ILP-98, Madison, Wisconsin, USA, July 22\u201324, 1998, Proceedings, Lecture notes in computer science (Vol. 1446, pp. 80\u201394). Springer. https:\/\/doi.org\/10.1007\/BFb0027312 .","DOI":"10.1007\/BFb0027312"},{"key":"5746_CR25","doi-asserted-by":"crossref","unstructured":"Krogel, M. A., & Wrobel, S. (2001). Transformation-based learning using multirelational aggregation. In ILP (pp. 142\u2013155). Springer.","DOI":"10.1007\/3-540-44797-0_12"},{"issue":"2","key":"5746_CR26","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/s10994-010-5208-5","volume":"83","author":"O Kuzelka","year":"2011","unstructured":"Kuzelka, O., & Zelezn\u00fd, F. (2011). Block-wise construction of tree-like relational features with monotone reducibility and redundancy. Machine Learning, 83(2), 163\u2013192. https:\/\/doi.org\/10.1007\/s10994-010-5208-5 .","journal-title":"Machine Learning"},{"key":"5746_CR27","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1007\/978-1-4899-7687-1_686","volume-title":"Encyclopedia of Machine Learning and Data Mining","author":"N Lachiche","year":"2017","unstructured":"Lachiche, N. (2017). Propositionalization. In C. Sammut & G. I. Webb (Eds.), Encyclopedia of Machine Learning and Data Mining (pp. 1025\u20131031). Boston, MA: Springer. https:\/\/doi.org\/10.1007\/978-1-4899-7687-1_686 ."},{"key":"5746_CR28","unstructured":"Lachiche, N., & Flach, P. (1999). 1BC: A first-order bayesian classifier. In Proceedings of the 9th international workshop on inductive logic programming (pp. 92\u2013103), Springer."},{"key":"5746_CR29","unstructured":"Lachiche, N., & Flach, P. (2002). 1BC2: A true first-order Bayesian classifier. In Proceedings of the 12th international conference on inductive logic programming (pp. 133\u2013148). Springer."},{"key":"5746_CR30","unstructured":"Landwehr, N., Kersting, K., & Raedt, L. D. (2007). Integrating na\u00efve bayes and FOIL. Journal of Machine Learning Research 8:481\u2013507. http:\/\/dl.acm.org\/citation.cfm?id=1314516 ."},{"key":"5746_CR31","doi-asserted-by":"publisher","unstructured":"Lavrac, N., Dzeroski, S., & Grobelnik, M. (1991). Learning nonrecursive definitions of relations with LINUS. In Y. Kodratoff (Ed.), Machine Learning\u2014EWSL-91, European working session on learning, Porto, Portugal, March 6\u20138, 1991, Proceedings, Lecture notes in computer science (Vol. 482, pp. 265\u2013281). Springer. https:\/\/doi.org\/10.1007\/BFb0017020 .","DOI":"10.1007\/BFb0017020"},{"key":"5746_CR32","doi-asserted-by":"publisher","unstructured":"Liu, H., Yin, X., & Han, J. (2005). An efficient multi-relational na\u00efve bayesian classifier based on semantic relationship graph. In Proceedings of the 4th international workshop on multi-relational mining, ACM, New York, NY, USA, MRDM\u201905 (pp. 39\u201348). https:\/\/doi.org\/10.1145\/1090193.1090200 .","DOI":"10.1145\/1090193.1090200"},{"key":"5746_CR33","unstructured":"Lodhi, H., & Muggleton, S. (2005). Is mutagenesis still challenging? In Late-breaking papers of the international conference on inductive logic programming (pp. 35\u201340)."},{"key":"5746_CR34","doi-asserted-by":"publisher","unstructured":"Meena, L., & Devi, V.S. (2015). Prototype selection on large and streaming data. In S. Arik, T. Huang, W. K. Lai, Q. Liu (Eds.), Neural information processing\u201422nd international conference, ICONIP 2015, Istanbul, Turkey, November 9\u201312, 2015, Proceedings, Part I, Lecture notes in computer science (Vol. 9489, pp. 671\u2013679). Springer. https:\/\/doi.org\/10.1007\/978-3-319-26532-2_74 .","DOI":"10.1007\/978-3-319-26532-2_74"},{"issue":"17\u201318","key":"5746_CR35","doi-asserted-by":"publisher","first-page":"6442","DOI":"10.1016\/j.eswa.2015.04.017","volume":"42","author":"M Perovsek","year":"2015","unstructured":"Perovsek, M., Vavpetic, A., Kranjc, J., Cestnik, B., & Lavrac, N. (2015). Wordification: Propositionalization by unfolding relational data into bags of words. Expert Systems with Applications, 42(17\u201318), 6442\u20136456. https:\/\/doi.org\/10.1016\/j.eswa.2015.04.017 .","journal-title":"Expert Systems with Applications"},{"key":"5746_CR36","unstructured":"Provost, F., & Domingos, P. (2001). Well-trained pets: Improving probability estimation trees. Technical report CeDER #IS-00-04, New York University."},{"key":"5746_CR37","volume-title":"C4.5: Programs for machine learning","author":"J Quinlan","year":"1993","unstructured":"Quinlan, J. (1993). C4.5: Programs for machine learning. Burlington: Morgan Kaufmann."},{"key":"5746_CR38","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1016\/0005-1098(78)90005-5","volume":"14","author":"J Rissanen","year":"1978","unstructured":"Rissanen, J. (1978). Modeling by shortest data description. Automatica, 14, 465\u2013471.","journal-title":"Automatica"},{"issue":"2","key":"5746_CR39","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1214\/aos\/1176346150","volume":"11","author":"J Rissanen","year":"1983","unstructured":"Rissanen, J. (1983). A universal prior for integers and estimation by minimum description length. Annals of Statistics, 11(2), 416\u2013431.","journal-title":"Annals of Statistics"},{"issue":"2","key":"5746_CR40","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s10994-010-5193-8","volume":"83","author":"L Schietgat","year":"2011","unstructured":"Schietgat, L., Costa, F., Ramon, J., & Raedt, L. D. (2011). Effective feature construction by maximum common subgraph sampling. Machine Learning, 83(2), 137\u2013161. https:\/\/doi.org\/10.1007\/s10994-010-5193-8 .","journal-title":"Machine Learning"},{"key":"5746_CR41","doi-asserted-by":"crossref","unstructured":"Shannon, C. (1948). A mathematical theory of communication. Technical Report 27, Bell systems technical journal.","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"5746_CR42","unstructured":"Srinivasan, A., Muggleton, S., King, R., Sternberg, M. (1994). Mutagenesis: ILP experiments in a non-determinate biological domain. In S. Wrobel (Ed.), Proceedings of the 4th international workshop on inductive logic programming (ILP\u201994) (Vol 237, pp. 217\u2013232). GMD-Studien."},{"issue":"1\u20133","key":"5746_CR43","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s10994-006-8713-9","volume":"64","author":"A Assche Van","year":"2006","unstructured":"Van Assche, A., Vens, C., Blockeel, H., & D\u017eeroski, S. (2006). First order random forests: Learning relational classifiers with complex aggregates. Machine Learning, 64(1\u20133), 149\u2013182.","journal-title":"Machine Learning"},{"issue":"1","key":"5746_CR44","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1145\/3147.3165","volume":"11","author":"J Vitter","year":"1985","unstructured":"Vitter, J. (1985). Random sampling with a reservoir. ACM Transactions on Mathematical Software, 11(1), 37\u201357.","journal-title":"ACM Transactions on Mathematical Software"},{"key":"5746_CR45","doi-asserted-by":"publisher","unstructured":"Yin, X., Han, J., Yang, J., & Yu, P. S. (2004). Crossmine: Efficient classification across multiple database relations. In Z. M. \u00d6zsoyoglu, & S. B. Zdonik (Eds.), Proceedings of the 20th international conference on data engineering, ICDE 2004, 30 March\u20132 April 2004, Boston, MA, USA (pp. 399\u2013410). IEEE Computer Society. https:\/\/doi.org\/10.1109\/ICDE.2004.1320014 .","DOI":"10.1109\/ICDE.2004.1320014"},{"issue":"1\u20132","key":"5746_CR46","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s10994-006-5834-0","volume":"62","author":"F Zelezn\u00fd","year":"2006","unstructured":"Zelezn\u00fd, F., & Lavrac, N. (2006). Propositionalization-based relational subgroup discovery with RSD. Machine Learning, 62(1\u20132), 33\u201363. https:\/\/doi.org\/10.1007\/s10994-006-5834-0 .","journal-title":"Machine Learning"},{"key":"5746_CR47","unstructured":"Zhou, C. (2015). Conformal and venn predictors for multi-probabilistic predictions and their applications. Ph.D. thesis, Royal Holloway, University of London."},{"key":"5746_CR48","first-page":"1609","volume-title":"Advances in Neural Information Processing Systems (NIPS\u201906)","author":"Zh Zhou","year":"2007","unstructured":"Zhou, Zh, & Zhang, M. L. (2007). Multi-instance multi-label learning with application to scene classification. In B. Sch\u00f6lkopf, J. Platt, & T. Hofmann (Eds.), Advances in Neural Information Processing Systems (NIPS\u201906) (pp. 1609\u20131616). Cambridge, MA: MIT Press."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-018-5746-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-018-5746-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-018-5746-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,8]],"date-time":"2020-11-08T03:47:57Z","timestamp":1604807277000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-018-5746-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,22]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,2]]}},"alternative-id":["5746"],"URL":"https:\/\/doi.org\/10.1007\/s10994-018-5746-9","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8,22]]},"assertion":[{"value":"8 November 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}