{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T21:28:12Z","timestamp":1770154092152,"version":"3.49.0"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2011,7]]},"DOI":"10.1007\/s10618-010-0202-x","type":"journal-article","created":{"date-parts":[[2010,10,15]],"date-time":"2010-10-15T06:47:20Z","timestamp":1287125240000},"page":"169-214","source":"Crossref","is-referenced-by-count":213,"title":["Krimp: mining itemsets that compress"],"prefix":"10.1007","volume":"23","author":[{"given":"Jilles","family":"Vreeken","sequence":"first","affiliation":[]},{"given":"Matthijs","family":"van Leeuwen","sequence":"additional","affiliation":[]},{"given":"Arno","family":"Siebes","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,10,16]]},"reference":[{"key":"202_CR1","unstructured":"Agrawal R, Mannila H, Srikant R, Toivonen H, Verkamo AI (1996) Fast discovery of association rules. In: Advances in knowledge discovery and data mining, AAAI, pp 307\u2013328"},{"key":"202_CR2","doi-asserted-by":"crossref","unstructured":"Bathoorn R, Koopman A, Siebes A (2006) Reducing the frequent pattern set. In: Proceedings of the ICDM-workshops\u201906, pp 55\u201359","DOI":"10.1109\/ICDMW.2006.140"},{"key":"202_CR3","doi-asserted-by":"crossref","unstructured":"Bayardo R (1998) Efficiently mining long patterns from databases. In: Proceedings of SIGMOD\u201998, pp 85\u201393","DOI":"10.1145\/276304.276313"},{"key":"202_CR4","doi-asserted-by":"crossref","unstructured":"Bringmann B, Zimmermann A (2007) The chosen few: on identifying valuable patterns. In: Proceedings of the ICDM\u201907, pp 63\u201372","DOI":"10.1109\/ICDM.2007.85"},{"key":"202_CR5","doi-asserted-by":"crossref","unstructured":"Calders T, Goethals B (2002) Mining all non-derivable frequent itemsets. In: Proceedings of the ECML PKDD\u201902, pp 74\u201385","DOI":"10.1007\/3-540-45681-3_7"},{"key":"202_CR6","doi-asserted-by":"crossref","unstructured":"Chakrabarti D, Papadimitriou S, Modha DS, Faloutsos C (2004) Fully automatic cross-associations. In: Proceedings of KDD\u201904, pp 79\u201388","DOI":"10.1145\/1014052.1014064"},{"key":"202_CR7","unstructured":"Chakrabarti S, Sarawagi S, Dom B (1998) Mining surprising patterns using temporal description length. In: Proceedings of VLDB\u201998, Morgan Kaufmann, San Francisco, pp 606\u2013617"},{"issue":"3","key":"202_CR8","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1007\/s10115-006-0039-1","volume":"12","author":"V Chandola","year":"2007","unstructured":"Chandola V, Kumar V (2007) Summarization\u2014compressing data into an informative representation. Knowl Inf Syst 12(3): 355\u2013378","journal-title":"Knowl Inf Syst"},{"key":"202_CR9","unstructured":"Coenen F (2003) The LUCS\u2013KDD discretised\/normalised ARM and CARM data library. http:\/\/www.csc.liv.ac.uk\/~frans\/KDD\/Software\/LUCS-KDD-DN\/DataSets\/dataSets.html"},{"key":"202_CR10","unstructured":"Coenen F (2004) The LUCS\u2013KDD software library. http:\/\/www.csc.liv.ac.uk\/~frans\/KDD\/Software"},{"key":"202_CR11","volume-title":"Elements of information theory, 2nd edn","author":"T Cover","year":"2006","unstructured":"Cover T, Thomas J (2006) Elements of information theory, 2nd edn. John Wiley and Sons, New York"},{"key":"202_CR12","unstructured":"Cr\u00e9milleux B, Boulicaut JF (2002) Simplest rules characterizing classes generated by \u03b4-free sets. In: Proceedings of KBSAAI\u201902, pp 33\u201346"},{"key":"202_CR13","volume-title":"Pattern classification and scene analysis","author":"R Duda","year":"1973","unstructured":"Duda R, Hart P (1973) Pattern classification and scene analysis. John Wiley and Sons, New York"},{"issue":"1","key":"202_CR14","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10618-006-0057-3","volume":"15","author":"C Faloutsos","year":"2007","unstructured":"Faloutsos C, Megalooikonomou V (2007) On data mining, compression and Kolmogorov complexity. Data Min Knowl Discov 15(1): 3\u201320","journal-title":"Data Min Knowl Discov"},{"key":"202_CR15","doi-asserted-by":"crossref","unstructured":"Geerts F, Goethals B, Mielik\u00e4inen T (2004) Tiling databases. In: Proceedings of DS\u201904, pp 278\u2013289","DOI":"10.1007\/978-3-540-30214-8_22"},{"issue":"3","key":"202_CR16","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1145\/1297332.1297338","volume":"1","author":"A Gionis","year":"2007","unstructured":"Gionis A, Mannila H, Mielik\u00e4inen T, Tsaparas P (2007) Assessing data mining results via swap randomization. ACM Trans Knowl Discov Data 1(3): 14","journal-title":"ACM Trans Knowl Discov Data"},{"key":"202_CR17","doi-asserted-by":"crossref","unstructured":"Goethals B, Zaki MJ (2003) Frequent itemset mining implementations repository (FIMI). http:\/\/fimi.cs.helsinki.fi","DOI":"10.1145\/1007730.1007744"},{"key":"202_CR18","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1114.001.0001","volume-title":"Advances in minimum description length","author":"PD Gr\u00fcnwald","year":"2005","unstructured":"Gr\u00fcnwald PD (2005) Minimum description length tutorial. In: Gr\u00fcnwald P, Myung I (eds) Advances in minimum description length. MIT Press, Cambridge"},{"key":"202_CR19","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4643.001.0001","volume-title":"The minimum description length principle","author":"PD Gr\u00fcnwald","year":"2007","unstructured":"Gr\u00fcnwald PD (2007) The minimum description length principle. MIT Press, Cambridge"},{"key":"202_CR20","volume-title":"Pattern detection and discovery","year":"2002","unstructured":"Hand, D, Adams, N, Bolton, R (eds) (2002) Pattern detection and discovery. Springer, New York"},{"key":"202_CR21","doi-asserted-by":"crossref","unstructured":"Heikinheimo H, Hinkkanen E, Mannila H, Mielik\u00e4inen T, Sepp\u00e4nen JK (2007) Finding low-entropy sets and trees from binary data. In: Proceedings of KDD\u201907, pp 350\u2013359","DOI":"10.1145\/1281192.1281232"},{"key":"202_CR22","doi-asserted-by":"crossref","unstructured":"Heikinheimo H, Vreeken J, Siebes A, Mannila H (2009) Low-entropy set selection. In: Proceedings of SDM\u201909, pp 569\u2013579","DOI":"10.1137\/1.9781611972795.49"},{"key":"202_CR23","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/978-1-4684-2001-2_9","volume-title":"Proceedings of a symposium on the complexity of computer computations","author":"RM Karp","year":"1972","unstructured":"Karp RM (1972) Reducibility among combinatorial problems. In: Miller R, Thatcher J (eds) Proceedings of a symposium on the complexity of computer computations. Plenum Press, New York, USA, pp 85\u2013103"},{"key":"202_CR24","doi-asserted-by":"crossref","unstructured":"Keogh E, Lonardi S, Ratanamahatana CA (2004) Towards parameter-free data mining. In: Proceedings of KDD\u201904, pp 206\u2013215","DOI":"10.1145\/1014052.1014077"},{"issue":"1","key":"202_CR25","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s10618-006-0049-3","volume":"14","author":"E Keogh","year":"2007","unstructured":"Keogh E, Lonardi S, Ratanamahatana CA, Wei L, Lee SH, Handley J (2007) Compression-based data mining of sequential data. Data Min Knowl Discov 14(1): 99\u2013129","journal-title":"Data Min Knowl Discov"},{"key":"202_CR26","doi-asserted-by":"crossref","unstructured":"Knobbe AJ, Ho EKY (2006a) Maximally informative k-itemsets and their efficient discovery. In: Proceedings of KDD\u201906, pp 237\u2013244","DOI":"10.1145\/1150402.1150431"},{"key":"202_CR27","doi-asserted-by":"crossref","unstructured":"Knobbe AJ, Ho EKY (2006b) Pattern teams. In: Proceedings of the ECML PKDD\u201906, pp 577\u2013584","DOI":"10.1007\/11871637_58"},{"key":"202_CR28","doi-asserted-by":"crossref","unstructured":"Kohavi R, Brodley C, Frasca B, Mason L, Zheng Z (2000) KDD-Cup 2000 organizers\u2019 report: peeling the onion. SIGKDD Explor 2(2):86\u201398. http:\/\/www.ecn.purdue.edu\/KDDCUP","DOI":"10.1145\/380995.381033"},{"key":"202_CR29","doi-asserted-by":"crossref","unstructured":"Koopman A, Siebes A (2008) Discovering relational items sets efficiently. In: Zaki M, Wang K (eds) Proceedings of SDM\u201908, SIAM, pp 108\u2013119","DOI":"10.1137\/1.9781611972788.10"},{"key":"202_CR30","doi-asserted-by":"crossref","unstructured":"Koopman A, Siebes A (2009) Characteristic relational patterns. In: Proceedings of KDD\u201909, pp 437\u2013446","DOI":"10.1145\/1557019.1557071"},{"key":"202_CR31","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3860-5","volume-title":"An introduction to Kolmogorov complexity and its applications","author":"M Li","year":"1993","unstructured":"Li M, Vit\u00e1nyi P (1993) An introduction to Kolmogorov complexity and its applications. Springer, New York"},{"key":"202_CR32","unstructured":"Liu B, Hsu W, Ma Y (1998) Integrating classification and association rule mining. In: Proceedings of KDD\u201998, pp 80\u201386"},{"key":"202_CR33","unstructured":"Liu G, Lu H, Yu JX, Wei W, Xiao X (2004) AFOPT: an efficient implementation of pattern growth approach. In: Proceedings of the 2nd workshop on frequent itemset mining implementations"},{"key":"202_CR34","unstructured":"Mannila H, Toivonen H (1996) Multiple uses of frequent sets and condensed representations. In: Proceedings of KDD\u201996, pp 189\u2013194"},{"key":"202_CR35","doi-asserted-by":"crossref","unstructured":"Mannila H, Toivonen H (1997) Levelwise search and borders of theories in knowledge discovery. Data mining and knowledge discovery, pp 241\u2013258","DOI":"10.1023\/A:1009796218281"},{"key":"202_CR36","doi-asserted-by":"crossref","unstructured":"Mehta M, Agrawal R, Rissanen J (1996) Sliq: a fast scalable classifier for data mining. In: Advances in database technology. Springer, NY, pp 18\u201332","DOI":"10.1007\/BFb0014141"},{"key":"202_CR37","doi-asserted-by":"crossref","unstructured":"Meretakis D, Lu H, W\u00fcthrich B (2000) A study on the performance of large bayes classifier. In: Proceedings of the ECML\u201900, pp 271\u2013279","DOI":"10.1007\/3-540-45164-1_29"},{"key":"202_CR38","doi-asserted-by":"crossref","unstructured":"Mielik\u00e4inen T, Mannila H (2003) The pattern ordering problem. In: Proceedings of the ECML PKDD\u201903, pp 327\u2013338","DOI":"10.1007\/978-3-540-39804-2_30"},{"key":"202_CR39","volume-title":"The atlas of European mammals","author":"AJ Mitchell-Jones","year":"1999","unstructured":"Mitchell-Jones AJ, Amori G, Bogdanowicz W, Krystufek B, Reijnders PJH, Spitzenberger F, Stubbe M, Thissen JBM, Vohralik V, Zima J (1999) The atlas of European mammals. Academic Press, London"},{"key":"202_CR40","volume-title":"Local pattern detection","year":"2005","unstructured":"Morik, K, Boulicaut, JF, Siebes, A (eds) (2005) Local pattern detection. Springer, New York"},{"key":"202_CR41","doi-asserted-by":"crossref","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)","DOI":"10.1038\/sj.onc.1209717"},{"key":"202_CR42","doi-asserted-by":"crossref","unstructured":"Pasquier N, Bastide Y, Taouil R, Lakhal L (1999) Discovering frequent closed itemsets for association rules. In: Proceedings of the ICDT\u201999, pp 398\u2013416","DOI":"10.1007\/3-540-49257-7_25"},{"key":"202_CR43","unstructured":"Pfahringer B (1995) Compression-based feature subset selection. In: Proceedings of the IJCAI\u201995 workshop on data engineering for inductive learning, pp 109\u2013119"},{"key":"202_CR44","volume-title":"C4.5: programs for machine learning","author":"J Quinlan","year":"1993","unstructured":"Quinlan J (1993b) C4.5: programs for machine learning. Morgan-Kaufmann, Los Altos"},{"key":"202_CR45","doi-asserted-by":"crossref","unstructured":"Quinlan J (1993b) FOIL: a midterm report. In: Proceedings of the ECML\u201993","DOI":"10.1007\/3-540-56602-3_124"},{"issue":"1","key":"202_CR46","doi-asserted-by":"crossref","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(1): 465\u2013471","journal-title":"Automatica"},{"key":"202_CR47","doi-asserted-by":"crossref","unstructured":"Siebes A, Vreeken J, van Leeuwen M (2006) Item sets that compress. In: Proceedings of SDM\u201906, pp 393\u2013404","DOI":"10.1137\/1.9781611972764.35"},{"key":"202_CR48","doi-asserted-by":"crossref","unstructured":"Sun J, Faloutsos C, Papadimitriou S, Yu PS (2007) Graphscope: parameter-free mining of large time-evolving graphs. In: Proceedings of KDD\u201907, pp 687\u2013696","DOI":"10.1145\/1281192.1281266"},{"key":"202_CR49","doi-asserted-by":"crossref","unstructured":"Tatti N, Vreeken J (2008) Finding good itemsets by packing data. In: Proceedings of the ICDM\u201908, pp 588\u2013597","DOI":"10.1109\/ICDM.2008.39"},{"key":"202_CR50","unstructured":"van Leeuwen M, Siebes A (2008) Streamkrimp: detecting change in data streams. In: Proceedings of ECMLPKDD\u201908, Springer, Heidelberg, pp 672\u2013687"},{"key":"202_CR51","doi-asserted-by":"crossref","unstructured":"van Leeuwen M, Vreeken J, Siebes A (2006) Compression picks the item sets that matter. In: Proceedings of the ECML PKDD\u201906, pp 585\u2013592","DOI":"10.1007\/11871637_59"},{"issue":"2","key":"202_CR52","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/s10618-009-0137-2","volume":"19","author":"M Leeuwen van","year":"2009","unstructured":"van Leeuwen M, Vreeken J, Siebes A (2009) Identifying the components. Data Min Knowl Discov 19(2): 173\u2013292","journal-title":"Data Min Knowl Discov"},{"key":"202_CR53","doi-asserted-by":"crossref","unstructured":"Vreeken J, Siebes A (2008) Filling in the blanks\u2014Krimp minimisation for missing data. In: Proceedings of the ICDM\u201908, pp 1067\u20131072","DOI":"10.1109\/ICDM.2008.40"},{"key":"202_CR54","doi-asserted-by":"crossref","unstructured":"Vreeken J, van Leeuwen M, Siebes A (2007a) Characterising the difference. In: Proceedings of KDD\u201907, pp 765\u2013774","DOI":"10.1145\/1281192.1281274"},{"key":"202_CR55","doi-asserted-by":"crossref","unstructured":"Vreeken J, van Leeuwen M, Siebes A (2007b) Preserving privacy through data generation. In: Proceedings of the ICDM\u201907, pp 685\u2013690","DOI":"10.1109\/ICDM.2007.25"},{"key":"202_CR56","volume-title":"Statistical and inductive inference by minimum message length","author":"C Wallace","year":"2005","unstructured":"Wallace C (2005) Statistical and inductive inference by minimum message length. Springer, New York"},{"key":"202_CR57","doi-asserted-by":"crossref","unstructured":"Wang J, Karypis G (2005) HARMONY: efficiently mining the best rules for classification. In: Proceedings of SDM\u201905, pp 205\u2013216","DOI":"10.1137\/1.9781611972757.19"},{"issue":"1","key":"202_CR58","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10115-005-0216-7","volume":"9","author":"J Wang","year":"2006","unstructured":"Wang J, Karypis G (2006) On efficiently summarizing categorical databases. Knowl Inf Syst 9(1): 19\u201337","journal-title":"Knowl Inf Syst"},{"key":"202_CR59","doi-asserted-by":"crossref","unstructured":"Wang C, Parthasarathy S (2006) Summarizing itemset patterns using probabilistic models. In: Proceedings of KDD\u201906, pp 730\u2013735","DOI":"10.1145\/1150402.1150495"},{"key":"202_CR60","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1001\/jama.1961.03040290005002","volume":"177","author":"H Warner","year":"1961","unstructured":"Warner H, Toronto A, Veasey L, Stephenson R (1961) A mathematical model for medical diagnosis, application to congenital heart disease. J Am Med Assoc 177: 177\u2013184","journal-title":"J Am Med Assoc"},{"key":"202_CR61","volume-title":"Data mining: practical machine learning tools and techniques","author":"I Witten","year":"2005","unstructured":"Witten I, Frank E (2005) Data mining: practical machine learning tools and techniques. 2nd edn. Morgan Kaufmann, San Francisco","edition":"2"},{"key":"202_CR62","doi-asserted-by":"crossref","unstructured":"Xiang Y, Jin R, Fuhry D, Dragan FF (2008) Succinct summarization of transactional databases: an overlapped hyperrectangle scheme. In: Proceedings of KDD\u201908, pp 758\u2013766","DOI":"10.1145\/1401890.1401981"},{"key":"202_CR63","unstructured":"Xin D, Han J, Yan X, Cheng H (2005) Mining compressed frequent-pattern sets. In: Proceedings of VLDB\u201905, pp 709\u2013720"},{"key":"202_CR64","doi-asserted-by":"crossref","unstructured":"Yan X, Cheng H, Han J, Xin D (2005) Summarizing itemset patterns: a profile-based approach. In: Proceedings of KDD\u201905, pp 314\u2013323","DOI":"10.1145\/1081870.1081907"},{"key":"202_CR65","doi-asserted-by":"crossref","unstructured":"Yin X, Han J (2003) CPAR: Classification based on predictive association rules. In: Proceedings of SDM\u201903, pp 331\u2013335","DOI":"10.1137\/1.9781611972733.40"},{"key":"202_CR66","doi-asserted-by":"crossref","unstructured":"Zhang X, Guozhu D, Ramamohanarao K (2000) Information-based classification by aggregating emerging patterns. In: Proceedings of IDEAL\u201900, pp 48\u201353","DOI":"10.1007\/3-540-44491-2_8"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-010-0202-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,5]],"date-time":"2019-06-05T14:15:41Z","timestamp":1559744141000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10618-010-0202-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,10,16]]},"references-count":66,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2011,7]]}},"alternative-id":["202"],"URL":"https:\/\/doi.org\/10.1007\/s10618-010-0202-x","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,10,16]]}}}