{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:26:22Z","timestamp":1759883182768,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032060686","type":"print"},{"value":"9783032060693","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-06069-3_14","type":"book-chapter","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T15:52:38Z","timestamp":1759852358000},"page":"165-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Similarity Based on\u00a0Resample Exposure"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9228-2417","authenticated-orcid":false,"given":"Anton","family":"Danholt Lautrup","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2107-5589","authenticated-orcid":false,"given":"Hafiz","family":"Saud Arshad","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4783-9893","authenticated-orcid":false,"given":"Tobias","family":"Hyrup","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7045-3998","authenticated-orcid":false,"given":"Muhammad","family":"Rajabinasab","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7713-4208","authenticated-orcid":false,"given":"Arthur","family":"Zimek","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4000-5570","authenticated-orcid":false,"given":"Peter","family":"Schneider-Kamp","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"issue":"1","key":"14_CR1","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/bf00153759","volume":"6","author":"DW Aha","year":"1991","unstructured":"Aha, D.W., Kibler, D., Albert, M.K.: Instance-based learning algorithms. Mach. Learn. 6(1), 37\u201366 (1991). https:\/\/doi.org\/10.1007\/bf00153759","journal-title":"Mach. Learn."},{"key":"14_CR2","doi-asserted-by":"publisher","unstructured":"Boriah, S., Chandola, V., Kumar, V.: Similarity measures for categorical data: a comparative evaluation. In: Proceedings of the 2008 SIAM International Conference on Data Mining. SIAM, April 2008. https:\/\/doi.org\/10.1137\/1.9781611972788.22","DOI":"10.1137\/1.9781611972788.22"},{"key":"14_CR3","doi-asserted-by":"publisher","unstructured":"Burnaby, T.P.: On a method for character weighting a similarity coefficient, employing the concept of information. Math. Geol. 2, 25\u201338 (1970). https:\/\/doi.org\/10.1007\/bf02332078","DOI":"10.1007\/bf02332078"},{"issue":"1","key":"14_CR4","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/tit.1967.1053964","volume":"13","author":"T Cover","year":"1967","unstructured":"Cover, T., Hart, P.: Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13(1), 21\u201327 (1967). https:\/\/doi.org\/10.1109\/tit.1967.1053964","journal-title":"IEEE Trans. Inf. Theory"},{"key":"14_CR5","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1\u201330 (2006)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR6","unstructured":"D\u2019Orazio, M.: Distances with mixed type variables some modified gower\u2019s coefficients (2021)"},{"key":"14_CR7","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1561\/0400000042","volume":"9","author":"C Dwork","year":"2013","unstructured":"Dwork, C., Roth, A.: The algorithmic foundations of differential privacy. Found. Trends Theor. Comput. Sci. 9, 211\u2013487 (2013). https:\/\/doi.org\/10.1561\/0400000042","journal-title":"Found. Trends Theor. Comput. Sci."},{"issue":"11","key":"14_CR8","doi-asserted-by":"publisher","first-page":"789","DOI":"10.2307\/1293644","volume":"16","author":"GF Estabrook","year":"1966","unstructured":"Estabrook, G.F., Rogers, D.J.: A general method of taxonomic description for a computed similarity measure. Bioscience 16(11), 789\u2013793 (1966). https:\/\/doi.org\/10.2307\/1293644","journal-title":"Bioscience"},{"key":"14_CR9","doi-asserted-by":"publisher","unstructured":"Everitt, B.S., Landau, S., Leese, M., Stahl, D.: Cluster Analysis. Wiley (2011). https:\/\/doi.org\/10.1002\/9780470977811","DOI":"10.1002\/9780470977811"},{"key":"14_CR10","unstructured":"F\u00e4rber, I., et al.: On using class-labels in evaluation of clusterings. In: MultiClust: 1st International Workshop on Discovering, Summarizing and Using Multiple Clusterings Held in Conjunction with KDD 2010, Washington, DC (2010)"},{"key":"14_CR11","doi-asserted-by":"publisher","first-page":"882","DOI":"10.2307\/2528080","volume":"22","author":"DW Goodall","year":"1966","unstructured":"Goodall, D.W.: A new similarity index based on probability. Biometrics 22, 882 (1966). https:\/\/doi.org\/10.2307\/2528080","journal-title":"Biometrics"},{"key":"14_CR12","doi-asserted-by":"publisher","unstructured":"G\u00f8ttcke, J.M.N., Zimek, A.: Handling class imbalance in k-nearest neighbor classification by balancing prior probabilities. In: Similarity Search and Applications SISAP, pp. 247\u2013261 (2021). https:\/\/doi.org\/10.1007\/978-3-030-89657-7_19","DOI":"10.1007\/978-3-030-89657-7_19"},{"key":"14_CR13","doi-asserted-by":"publisher","unstructured":"Gower, J.C.: A note on burnaby\u2019s character-weighted similarity coefficient. Math. Geosci. 2, 39\u201345 (1970). https:\/\/doi.org\/10.1007\/bf02332079","DOI":"10.1007\/bf02332079"},{"issue":"4","key":"14_CR14","doi-asserted-by":"publisher","first-page":"857","DOI":"10.2307\/2528823","volume":"27","author":"JC Gower","year":"1971","unstructured":"Gower, J.C.: A general coefficient of similarity and some of its properties. Biometrics 27(4), 857\u2013871 (1971). https:\/\/doi.org\/10.2307\/2528823","journal-title":"Biometrics"},{"key":"14_CR15","doi-asserted-by":"publisher","unstructured":"Hyrup, T., Lautrup, A.D., Zimek, A., Schneider-Kamp, P.: Sharing is cairing: characterizing principles and assessing properties of universal privacy evaluation for synthetic tabular data. Mach. Learn. Appl. 18, 100608 (2024). https:\/\/doi.org\/10.1016\/j.mlwa.2024.100608","DOI":"10.1016\/j.mlwa.2024.100608"},{"issue":"4","key":"14_CR16","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1109\/21.286391","volume":"24","author":"M Ichino","year":"1994","unstructured":"Ichino, M., Yaguchi, H.: Generalized minkowski metrics for mixed feature-type data analysis. IEEE Trans. Syst. Man Cybern. 24(4), 698\u2013708 (1994). https:\/\/doi.org\/10.1109\/21.286391","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"14_CR17","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316801","author":"L Kaufman","year":"1990","unstructured":"Kaufman, L., Rousseeuw, P.J.: Finding groups in data: an introduction to cluster analysis. Wiley (1990). https:\/\/doi.org\/10.1002\/9780470316801","journal-title":"Wiley"},{"key":"14_CR18","doi-asserted-by":"publisher","unstructured":"Lenssen, L., Stahmann, P., Janiesch, C., Schubert, E.: Archetype discovery from taxonomies: a method to cluster small datasets of categorical data. In: 57th Hawaii International Conference on System Sciences. HICSS, University of Hawaii at Manoa (2025). https:\/\/doi.org\/10.24251\/hicss.2025.145","DOI":"10.24251\/hicss.2025.145"},{"key":"14_CR19","doi-asserted-by":"publisher","unstructured":"Lumij\u00e4rvi, J., Laurikkala, J., Juhola, M.: A comparison of different heterogeneous proximity functions and euclidean distance. In: Proceedings of the 11th World Congress on Medical Informatics, San Francisco, California, USA, 7\u201311 September 2004. Stud. Health Technol. Inform., vol.\u00a0107, pp. 1362\u20131366. IOS Press (2004). https:\/\/doi.org\/10.3233\/978-1-60750-949-3-1362","DOI":"10.3233\/978-1-60750-949-3-1362"},{"issue":"3","key":"14_CR20","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1109\/34.990133","volume":"24","author":"P Mitra","year":"2002","unstructured":"Mitra, P., Murthy, C., Pal, S.: Unsupervised feature selection using feature similarity. IEEE Trans. Pattern Anal. Mach. Intell. 24(3), 301\u2013312 (2002). https:\/\/doi.org\/10.1109\/34.990133","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"14_CR21","doi-asserted-by":"publisher","first-page":"331","DOI":"10.2307\/1224438","volume":"48","author":"J Podani","year":"1999","unstructured":"Podani, J.: Extending gower\u2019s general coefficient of similarity to ordinal characters. Taxon 48(2), 331\u2013340 (1999). https:\/\/doi.org\/10.2307\/1224438","journal-title":"Taxon"},{"key":"14_CR22","doi-asserted-by":"publisher","unstructured":"Preud\u2019homme, G., et al.: Head-to-head comparison of clustering methods for heterogeneous data: a simulation-driven benchmark. Sci. Rep. 11(1) (2021). https:\/\/doi.org\/10.1038\/s41598-021-83340-8","DOI":"10.1038\/s41598-021-83340-8"},{"key":"14_CR23","doi-asserted-by":"publisher","unstructured":"Rajabinasab, M., Lautrup, A., Zimek, A.: Metrics for inter-dataset similarity with example applications in synthetic data and feature selection evaluation, pp. 527\u2013537. SIAM, January 2025. https:\/\/doi.org\/10.1137\/1.9781611978520.57","DOI":"10.1137\/1.9781611978520.57"},{"issue":"3","key":"14_CR24","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1093\/biomet\/66.3.605","volume":"66","author":"DW Scott","year":"1979","unstructured":"Scott, D.W.: On optimal and data-based histograms. Biometrika 66(3), 605\u2013610 (1979). https:\/\/doi.org\/10.1093\/biomet\/66.3.605","journal-title":"Biometrika"},{"issue":"12","key":"14_CR25","doi-asserted-by":"publisher","first-page":"1213","DOI":"10.1145\/7902.7906","volume":"29","author":"C Stanfill","year":"1986","unstructured":"Stanfill, C., Waltz, D.: Toward memory-based reasoning. Commun. ACM 29(12), 1213\u20131228 (1986). https:\/\/doi.org\/10.1145\/7902.7906","journal-title":"Commun. ACM"},{"key":"14_CR26","doi-asserted-by":"publisher","unstructured":"Sweeney, L.: k-anonymity: a model for protecting privacy. Int. J. Uncertain. Fuzziness Knowl. Based Syst. 10(5), 557\u2013570 (2002). https:\/\/doi.org\/10.1142\/s0218488502001648","DOI":"10.1142\/s0218488502001648"},{"key":"14_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1613\/jair.346","volume":"6","author":"DR Wilson","year":"1997","unstructured":"Wilson, D.R., Martinez, T.R.: Improved heterogeneous distance functions. J. Artif. Intell. Res. 6, 1\u201334 (1997). https:\/\/doi.org\/10.1613\/jair.346","journal-title":"J. Artif. Intell. Res."},{"issue":"8","key":"14_CR28","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.1109\/jbhi.2020.2980262","volume":"24","author":"J Yoon","year":"2020","unstructured":"Yoon, J., Drumright, L.N., Schaar, M.: Anonymization through data synthesis using generative adversarial networks (ads-gan). IEEE J. Biomed. Health Inform. 24(8), 2378\u20132388 (2020). https:\/\/doi.org\/10.1109\/jbhi.2020.2980262","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"14_CR29","doi-asserted-by":"publisher","unstructured":"Zimek, A., Filzmoser, P.: There and back again: outlier detection between statistical reasoning and data mining algorithms. WIREs Data Min. Knowl. Discov. 8(6) (2018). https:\/\/doi.org\/10.1002\/widm.1280","DOI":"10.1002\/widm.1280"}],"container-title":["Lecture Notes in Computer Science","Similarity Search and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06069-3_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T15:52:41Z","timestamp":1759852361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06069-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"ISBN":["9783032060686","9783032060693"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06069-3_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,8]]},"assertion":[{"value":"8 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests."}},{"value":"SISAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Similarity Search and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Reykjavik","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Iceland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sisap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.sisap.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}