{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T07:14:21Z","timestamp":1758266061026},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2012,6,22]],"date-time":"2012-06-22T00:00:00Z","timestamp":1340323200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2012,9]]},"DOI":"10.1007\/s10618-012-0275-9","type":"journal-article","created":{"date-parts":[[2012,6,21]],"date-time":"2012-06-21T09:36:01Z","timestamp":1340271361000},"page":"173-207","source":"Crossref","is-referenced-by-count":13,"title":["Comparing apples and oranges: measuring differences between exploratory data mining results"],"prefix":"10.1007","volume":"25","author":[{"given":"Nikolaj","family":"Tatti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jilles","family":"Vreeken","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,6,22]]},"reference":[{"key":"275_CR1","doi-asserted-by":"crossref","unstructured":"Aggarwal CC, Wolf JL, Yu PS, Procopiuc C, Park JS (1999) Fast algorithms for projected clustering. In: Proceedings of the ACM international conference on management of data (SIGMOD), Philadelphia, PA, ACM, pp 61\u201372","DOI":"10.1145\/304182.304188"},{"key":"275_CR2","unstructured":"Agrawal R, Srikant R (1994) Fast algorithms for mining association rules. In: Proceedings of the 20th international conference on very large data bases (VLDB), Santiago de Chile, Chile, pp 487\u2013499"},{"key":"275_CR3","volume-title":"Elements of information theory","author":"TM Cover","year":"2006","unstructured":"Cover TM, Thomas JA (2006) Elements of information theory. Wiley, New York"},{"issue":"1","key":"275_CR4","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1214\/aop\/1176996454","volume":"3","author":"I Csisz\u00e1r","year":"1975","unstructured":"Csisz\u00e1r I (1975) I-divergence geometry of probability distributions and minimization problems. Ann Probab 3(1): 146\u2013158","journal-title":"Ann Probab"},{"issue":"5","key":"275_CR5","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.1214\/aoms\/1177692379","volume":"43","author":"J Darroch","year":"1972","unstructured":"Darroch J, Ratcliff D (1972) Generalized iterative scaling for log-linear models. Ann Math Stat 43(5): 1470\u20131480","journal-title":"Ann Math Stat"},{"key":"275_CR6","doi-asserted-by":"crossref","unstructured":"De Bie T (2011a) An information theoretic framework for data mining. In: Proceedings of the 17th ACM international conference on knowledge discovery and data mining (SIGKDD), San Diego, CA, ACM","DOI":"10.1145\/2020408.2020497"},{"key":"275_CR7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10618-010-0198-2","volume":"23","author":"T De Bie","year":"2011","unstructured":"De Bie T (2011b) Maximum entropy models and subjective interestingness: an application to tiles in binary databases. Data Min Knowl Discov 23: 1\u201340","journal-title":"Data Min Knowl Discov"},{"issue":"2","key":"275_CR8","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1666\/04087.1","volume":"32","author":"M Fortelius","year":"2006","unstructured":"Fortelius M, Gionis A, Jernvall J, Mannila H (2006) Spectral ordering and biochronology of European fossil mammals. Paleobiology 32(2): 206\u2013214","journal-title":"Paleobiology"},{"key":"275_CR9","doi-asserted-by":"crossref","unstructured":"Gallo A, Miettinen P, Mannila H (2008) Finding subgroups having several descriptions: algorithms for redescription mining. In: Proceedings of the 8th SIAM international conference on data mining (SDM), Atlanta, GA","DOI":"10.1137\/1.9781611972788.30"},{"issue":"1","key":"275_CR10","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s10115-010-0319-7","volume":"28","author":"GC Garriga","year":"2011","unstructured":"Garriga GC, Junttila E, Mannila H (2011) Banded structure in binary matrices. Knowl Inform Syst 28(1): 197\u2013226","journal-title":"Knowl Inform Syst"},{"key":"275_CR11","doi-asserted-by":"crossref","unstructured":"Geerts F, Goethals B, Mielik\u00e4inen T (2004) Tiling databases. In: Proceedings of discovery science, pp 278\u2013289","DOI":"10.1007\/978-3-540-30214-8_22"},{"key":"275_CR12","doi-asserted-by":"crossref","unstructured":"Gionis A, Mannila H, Sepp\u00e4nen JK (2004) Geometric and combinatorial tiles in 0\u20131 data. In: Proceedings of the 8th European conference on principles and practice of knowledge discovery in databases (PKDD), Pisa, Italy, pp 173\u2013184","DOI":"10.1007\/978-3-540-30116-5_18"},{"key":"275_CR13","doi-asserted-by":"crossref","unstructured":"Hanhij\u00e4rvi S, Ojala M, Vuokko N, Puolam\u00e4ki K, Tatti N, Mannila H (2009) Tell me something I don\u2019t know: randomization strategies for iterative data mining. In: Proceedings of the 15th ACM international conference on knowledge discovery and data mining (SIGKDD), Paris, France, ACM, pp 379\u2013388","DOI":"10.1145\/1557019.1557065"},{"key":"275_CR14","doi-asserted-by":"crossref","unstructured":"Hollm\u00e9n J, Sepp\u00e4nen JK, Mannila H (2003) Mixture models and frequent sets: combining global and local methods for 0\u20131 data. In: Proceedings of the 3rd SIAM international conference on data mining (SDM), San Francisco, CA","DOI":"10.1137\/1.9781611972733.32"},{"issue":"9","key":"275_CR15","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1109\/PROC.1982.12425","volume":"70","author":"E Jaynes","year":"1982","unstructured":"Jaynes E (1982) On the rationale of maximum-entropy methods. Proc IEEE 70(9): 939\u2013952","journal-title":"Proc IEEE"},{"key":"275_CR16","doi-asserted-by":"crossref","unstructured":"Knobbe A, Ho E (2006) Pattern teams. In: Proceedings of the 10th European conference on principles and practice of knowledge discovery in databases (PKDD), Berlin, Germany, vol 4213. Springer, pp 577\u2013584","DOI":"10.1007\/11871637_58"},{"key":"275_CR17","unstructured":"Kontonasios KN, De Bie T (2010) An information-theoretic approach to finding noisy tiles in binary databases. In: Proceedings of the 10th SIAM international conference on data mining (SDM), Columbus, OH, SIAM, pp 153\u2013164"},{"key":"275_CR18","doi-asserted-by":"crossref","unstructured":"Kontonasios KN, Vreeken J, De Bie T (2011) Maximum entropy modelling for assessing results on real-valued data. In: Proceedings of the 11th IEEE international conference on data mining (ICDM), Vancouver, Canada, ICDM","DOI":"10.1109\/ICDM.2011.98"},{"issue":"2","key":"275_CR19","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1023\/A:1022859003006","volume":"51","author":"LI Kuncheva","year":"2003","unstructured":"Kuncheva LI, Whitaker CJ (2003) Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy. Mach Learn 51(2): 181\u2013207","journal-title":"Mach Learn"},{"key":"275_CR20","unstructured":"MacQueen J (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statististics and probability (Berkeley, Calif., 1965\/66), vol I: Statistics. Univ. California Press, Berkeley, pp 281\u2013297"},{"key":"275_CR21","doi-asserted-by":"crossref","unstructured":"Mampaey M, Vreeken J (2010) Summarising data by clustering items. In: Proceedings of the European conference on machine learning and principles and practice of knowledge discovery in databases (ECML PKDD), Barcelona, Spain. Springer, pp 321\u2013336","DOI":"10.1007\/978-3-642-15883-4_21"},{"key":"275_CR22","doi-asserted-by":"crossref","unstructured":"Mampaey M, Vreeken J (2012) Summarising categorical data by clustering attributes. Data Min Knowl Discov (in press)","DOI":"10.1007\/s10618-011-0246-6"},{"key":"275_CR23","doi-asserted-by":"crossref","unstructured":"Mampaey M, Tatti N, Vreeken J (2012) Succinctly summarizing data with itemsets. ACM Trans Knowl Discov Data (in press)","DOI":"10.1145\/2382577.2382580"},{"key":"275_CR24","doi-asserted-by":"crossref","unstructured":"Mannila H, Terzi E (2007) Nestedness and segmented nestedness. In: Proceedings of the 13th ACM international conference on knowledge discovery and data mining (SIGKDD), San Jose, CA, ACM, p 489","DOI":"10.1145\/1281192.1281245"},{"issue":"4","key":"275_CR25","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.ipl.2008.05.007","volume":"108","author":"P Miettinen","year":"2008","unstructured":"Miettinen P (2008) On the positive-negative partial set cover problem. Inform Process Lett 108(4): 219\u2013221","journal-title":"Inform Process Lett"},{"issue":"10","key":"275_CR26","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1109\/TKDE.2008.53","volume":"20","author":"P Miettinen","year":"2008","unstructured":"Miettinen P, Mielik\u00e4inen T, Gionis A, Das G, Mannila H (2008) The discrete basis problem. IEEE Trans Knowl Data Eng 20(10): 1348\u20131362","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"275_CR27","unstructured":"Mitchell-Jones A, Amori G, Bogdanowicz W, Krystufek B, Reijnders PH, Spitzenberger F, Stubbe M, Thissen J, Vohralik V, Zima J (1999) The Atlas of European Mammals. Academic Press"},{"key":"275_CR28","doi-asserted-by":"crossref","unstructured":"M\u00fcller E, G\u00fcnnemann S, Assent I, Seidl T (2009) Evaluating clustering in subspace projections of high dimensional data. In: Proceedings of the 35th international conference on very large databases (VLDB), Lyon, France, pp 1270\u20131281","DOI":"10.14778\/1687627.1687770"},{"issue":"55","key":"275_CR29","doi-asserted-by":"crossref","first-page":"7324","DOI":"10.1038\/sj.onc.1209717","volume":"25","author":"S Myllykangas","year":"2006","unstructured":"Myllykangas S, Himberg J, B\u00f6hling T, Nagy B, Hollm\u00e9n J, Knuutila S (2006) DNA copy number amplification profiling of human neoplasms. Oncogene 25(55): 7324\u20137332","journal-title":"Oncogene"},{"key":"275_CR30","doi-asserted-by":"crossref","unstructured":"Pensa RG, Robardet C, Boulicaut JF (2005) A bi-clustering framework for categorical data. In: Proceedings of the 9th European conference on principles and practice of knowledge discovery in databases (PKDD), Porto, Portugal, pp 643\u2013650","DOI":"10.1007\/11564126_68"},{"issue":"2","key":"275_CR31","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.ipl.2008.03.013","volume":"108","author":"K Puolam\u00e4ki","year":"2008","unstructured":"Puolam\u00e4ki K, Hanhij\u00e4rvi S, Garriga GC (2008) An approximation ratio for biclustering. Inform Process Lett 108(2): 45\u201349","journal-title":"Inform Process Lett"},{"key":"275_CR32","doi-asserted-by":"crossref","unstructured":"Ramakrishnan N, Kumar D, Mishra B, Potts M, Helm RF (2004) Turning cartwheels: an alternating algorithm for mining redescriptions. In: Proceedings of the 10th ACM international conference on knowledge discovery and data mining (SIGKDD), Seattle, WA, pp 266\u2013275","DOI":"10.1145\/1014052.1014083"},{"key":"275_CR33","unstructured":"Rasch G (1960) Probabilistic Models for Some Intelligence and Attainnment Tests. Danmarks paedagogiske Institut"},{"key":"275_CR34","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1109\/T-C.1969.222678","volume":"18","author":"J Sammon","year":"1969","unstructured":"Sammon J (1969) A nonlinear mapping for data structure analysis. IEEE Trans Comput 18: 401\u2013409","journal-title":"IEEE Trans Comput"},{"key":"275_CR35","doi-asserted-by":"crossref","unstructured":"Siebes A, Vreeken J, van Leeuwen M (2006) Item sets that compress. In: Proceedings of the 6th SIAM international conference on data mining (SDM), Bethesda, MD, SIAM, pp 393\u2013404","DOI":"10.1137\/1.9781611972764.35"},{"issue":"5","key":"275_CR36","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.ipl.2006.02.003","volume":"98","author":"N Tatti","year":"2006","unstructured":"Tatti N (2006) Computational complexity of queries based on itemsets. Inform Process Lett 98(5): 183\u2013187. doi: 10.1016\/j.ipl.2006.02.003","journal-title":"Inform Process Lett"},{"key":"275_CR37","first-page":"131","volume":"8","author":"N Tatti","year":"2007","unstructured":"Tatti N (2007) Distances between data sets based on summary statistics. J Mach Learn Res 8: 131\u2013154","journal-title":"J Mach Learn Res"},{"key":"275_CR38","unstructured":"Tatti N, Vreeken J (2011) Comparing apples and oranges: measuring differences between data mining results. In: Proceedings of the European conference on machine learning and principles and practice of knowledge discovery in databases (ECML PKDD), Athens, Greece. Springer, pp 398\u2013413"},{"key":"275_CR39","doi-asserted-by":"crossref","unstructured":"Vreeken J, van Leeuwen M, Siebes A (2007) Characterising the difference. In: Proceedings of the 13th ACM international conference on knowledge discovery and data mining (SIGKDD), San Jose, CA, pp 765\u2013774","DOI":"10.1145\/1281192.1281274"},{"issue":"1","key":"275_CR40","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/s10618-010-0202-x","volume":"23","author":"J Vreeken","year":"2011","unstructured":"Vreeken J, van Leeuwen M, Siebes A (2011) Krimp: mining itemsets that compress. Data Min Knowl Discov 23(1): 169\u2013214","journal-title":"Data Min Knowl Discov"},{"key":"275_CR41","doi-asserted-by":"crossref","unstructured":"Wang C, Parthasarathy S (2006) Summarizing itemset patterns using probabilistic models. In: Proceedings of the 12th ACM international conference on knowledge discovery and data mining (SIGKDD), Philadelphia, PA, pp 730\u2013735","DOI":"10.1145\/1150402.1150495"},{"issue":"2","key":"275_CR42","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s10618-010-0203-9","volume":"23","author":"Y Xiang","year":"2011","unstructured":"Xiang Y, Jin R, Fuhry D, Dragan F (2011) Summarizing transactional databases with overlapped hyperrectangles. Data Min Knowl Discov 23(2): 215\u2013251","journal-title":"Data Min Knowl Discov"},{"key":"275_CR43","doi-asserted-by":"crossref","unstructured":"Zaki MJ, Ramakrishnan N (2005) Reasoning about sets using redescription mining. In: Proceedings of the 11th ACM international conference on knowledge discovery and data mining (SIGKDD), Chicago, IL, ACM, pp 364\u2013373. doi: 10.1145\/1081870.1081912","DOI":"10.1145\/1081870.1081912"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-012-0275-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10618-012-0275-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-012-0275-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,30]],"date-time":"2019-06-30T01:11:30Z","timestamp":1561857090000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10618-012-0275-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,22]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2012,9]]}},"alternative-id":["275"],"URL":"https:\/\/doi.org\/10.1007\/s10618-012-0275-9","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,6,22]]}}}