{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T12:47:25Z","timestamp":1790254045423,"version":"4.1.0"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319078205","type":"print"},{"value":"9783319078212","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"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":[[2014]]},"DOI":"10.1007\/978-3-319-07821-2_8","type":"book-chapter","created":{"date-parts":[[2014,8,29]],"date-time":"2014-08-29T06:36:06Z","timestamp":1409294166000},"page":"165-198","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Mining and Using Sets of Patterns through Compression"],"prefix":"10.1007","author":[{"given":"Matthijs","family":"van Leeuwen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilles","family":"Vreeken","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2014,8,30]]},"reference":[{"issue":"1","key":"8_CR1","first-page":"444","volume":"55","author":"P. Adriaans","year":"2009","unstructured":"P. Adriaans and P. Vit\u00e1nyi. Approximation of the two-part MDL code. IEEE TIT, 55(1):444\u2013457, 2009.","journal-title":"IEEE TIT"},{"issue":"6","key":"8_CR2","first-page":"716","volume":"19","author":"H. Akaike","year":"1974","unstructured":"H. Akaike. A new look at the statistical model identification. IEEE TAC, 19(6):716\u2013723, 1974.","journal-title":"IEEE TAC"},{"key":"8_CR3","unstructured":"L. Akoglu, H. Tong, J. Vreeken, and C. Faloutsos. CompreX (refer MSP): Compression based anomaly detection. In CIKM. ACM, 2012."},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"L. Akoglu, J. Vreeken, H. Tong, N. Tatti, and C. Faloutsos. Mining connection pathways for marked nodes in large graphs. In SDM. SIAM, 2013.","DOI":"10.1137\/1.9781611972832.5"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"R. Bathoorn, A. Koopman, and A. Siebes. Reducing the frequent pattern set. In ICDM-Workshop, pages\u00a01\u20135, 2006.","DOI":"10.1109\/ICDMW.2006.140"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"C. B\u00f6hm, C. Faloutsos, J.-Y. Pan, and C. Plant. Robust information-theoretic clustering. In KDD, pages\u00a065\u201375, 2006.","DOI":"10.1145\/1150402.1150414"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"F. Bonchi, M. van Leeuwen, and A. Ukkonen. Characterizing uncertain data using compression. In SDM, pages\u00a0534\u2013545, 2011.","DOI":"10.1137\/1.9781611972818.46"},{"key":"8_CR8","unstructured":"S. Chakrabarti, S. Sarawagi, and B. Dom. Mining surprising patterns using temporal description length. In VLDB, pages\u00a0606\u2013617. Morgan Kaufmann, 1998."},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"D. Chakrabarti, S. Papadimitriou, D. S. Modha, and C. Faloutsos. Fully automatic cross-associations. In KDD, pages\u00a079\u201388, 2004.","DOI":"10.21236\/ADA459025"},{"issue":"3","key":"8_CR10","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/s10115-006-0039-1","volume":"12","author":"V. Chandola","year":"2007","unstructured":"V. Chandola and V. Kumar. Summarization \u2013 compressing data into an informative representation. Knowl. Inf. Sys., 12(3):355\u2013378, 2007.","journal-title":"Knowl. Inf. Sys"},{"issue":"4","key":"8_CR11","first-page":"1523","volume":"51","author":"R. Cilibrasi","year":"2005","unstructured":"R. Cilibrasi and P. Vit\u00e1nyi. Clustering by compression. IEEE TIT, 51(4):1523\u20131545, 2005.","journal-title":"IEEE TIT"},{"key":"8_CR12","unstructured":"T. M. Cover and J. A. Thomas. Elements of Information Theory. Wiley-Interscience New York, 2006."},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"T. De Bie. An information theoretic framework for data mining. In KDD, pages\u00a0564\u2013572. ACM, 2011.","DOI":"10.1145\/2020408.2020497"},{"issue":"1","key":"8_CR14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A. Dempster","year":"1977","unstructured":"A. Dempster, N. Laird, and D. Rubin. Maximum likelihood from incomplete data via the EM algorithm. J. R. Statist. Soc. B, 39(1):1\u201338, 1977.","journal-title":"J. R. Statist. Soc. B"},{"issue":"1","key":"8_CR15","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10618-006-0057-3","volume":"15","author":"C. Faloutsos","year":"2007","unstructured":"C. Faloutsos and V. Megalooikonomou. On data mining, compression and Kolmogorov complexity. Data Min. Knowl. Disc., 15(1):3\u201320, 2007.","journal-title":"Data Min. Knowl. Disc"},{"key":"8_CR16","unstructured":"U. Fayyad and K. Irani. Multi-interval discretization of continuous-valued attributes for classification learning. In UAI, pages\u00a01022\u20131027, 1993."},{"issue":"1","key":"8_CR17","doi-asserted-by":"publisher","first-page":"87","DOI":"10.2307\/2340521","volume":"85","author":"R. A. Fisher","year":"1922","unstructured":"R. A. Fisher. On the interpretation of \u03c72from contingency tables, and the calculation of P. Journal of the Royal Statistical Society, 85(1):87\u201394, 1922.","journal-title":"Journal of the Royal Statistical Society"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"F. Geerts, B. Goethals, and T. Mielik\u00e4inen. Tiling databases. In DS, pages\u00a0278\u2013289, 2004.","DOI":"10.1007\/978-3-540-30214-8_22"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"A. Gionis, H. Mannila, and J. K. Sepp\u00e4nen. Geometric and combinatorial tiles in 0-1 data. In PKDD, pages\u00a0173\u2013184. Springer, 2004.","DOI":"10.1007\/978-3-540-30116-5_18"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"P. Gr\u00fcnwald. The Minimum Description Length Principle. MIT Press, 2007.","DOI":"10.7551\/mitpress\/4643.001.0001"},{"issue":"12-13","key":"8_CR21","doi-asserted-by":"publisher","first-page":"1951","DOI":"10.1016\/j.artint.2011.05.002","volume":"175","author":"T. Guns","year":"2011","unstructured":"T. Guns, S. Nijssen, and L. D. Raedt. Itemset mining: A constraint programming perspective. Artif. Intell., 175(12-13):1951\u20131983, 2011.","journal-title":"Artif. Intell"},{"issue":"2-3","key":"8_CR22","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1016\/j.tcs.2005.09.015","volume":"348","author":"E. Halperin","year":"2005","unstructured":"E. Halperin and R. M. Karp. The minimum-entropy set cover problem. TCS, 348(2-3):240\u2013250, 2005.","journal-title":"TCS"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"H. Heikinheimo, J. K. Sepp\u00e4nen, E. Hinkkanen, H. Mannila, and T. Mielik\u00e4inen. Finding low-entropy sets and trees from binary data. In KDD, pages\u00a0350\u2013359, 2007.","DOI":"10.1145\/1281192.1281232"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"H. Heikinheimo, J. Vreeken, A. Siebes, and H. Mannila. Lowentropy set selection. In SDM, pages\u00a0569\u2013580, 2009.","DOI":"10.1137\/1.9781611972795.49"},{"issue":"9","key":"8_CR25","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1109\/PROC.1982.12425","volume":"70","author":"E. Jaynes","year":"1982","unstructured":"E. Jaynes. On the rationale of maximum-entropy methods. Proc. IEEE, 70(9):939\u2013952, 1982.","journal-title":"Proc. IEEE"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"U. Kang and C. Faloutsos. Beyond caveman communities: Hubs and spokes for graph compression and mining. In ICDM, pages\u00a0300\u2013309. IEEE, 2011.","DOI":"10.1109\/ICDM.2011.26"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"R. M. Karp. Reducibility among combinatorial problems. In Proc. Compl. Comp. Comput., pages\u00a085\u2013103, New York, USA, 1972.","DOI":"10.1007\/978-1-4684-2001-2_9"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"E. Keogh, S. Lonardi, and C. A. Ratanamahatana. Towards parameter-free data mining. In KDD, pages\u00a0206\u2013215, 2004.","DOI":"10.1145\/1014052.1014077"},{"issue":"1","key":"8_CR29","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s10618-006-0049-3","volume":"14","author":"E. Keogh","year":"2007","unstructured":"E. Keogh, S. Lonardi, C. A. Ratanamahatana, L. Wei, S.-H. Lee, and J. Handley. Compression-based data mining of sequential data. Data Min. Knowl. Disc., 14(1):99\u2013129, 2007.","journal-title":"Data Min. Knowl. Disc"},{"issue":"6","key":"8_CR30","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/j.ipl.2007.04.003","volume":"103","author":"P. Kontkanen","year":"2007","unstructured":"P. Kontkanen and P. Myllym\u00e4ki. A linear-time algorithm for computing the multinomial stochastic complexity. Inf. Process. Lett., 103(6):227\u2013233, 2007.","journal-title":"Inf. Process. Lett"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"P. Kontkanen, P. Myllym\u00e4ki, W. Buntine, J. Rissanen, and H. Tirri. An MDL framework for clustering. Technical report, HIIT, 2004. Technical Report 2004\u20136.","DOI":"10.7551\/mitpress\/1114.003.0018"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"A. Koopman and A. Siebes. Discovering relational items sets efficiently. In SDM, pages\u00a0108\u2013119, 2008.","DOI":"10.1137\/1.9781611972788.10"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"A. Koopman and A. Siebes. Characteristic relational patterns. In KDD, pages\u00a0437\u2013446, 2009.","DOI":"10.1145\/1557019.1557071"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"H. T. Lam, F. M\u00f6rchen, D. Fradkin, and T. Calders. Mining compressing sequential patterns. In SDM, 2012.","DOI":"10.1137\/1.9781611972825.28"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"H. T. Lam, T. Calders, J. Yang, F. Moerchen, and D. Fradkin.: Mining compressing sequential patterns in streams. In IDEA, pages\u00a054\u201362, 2013.","DOI":"10.1137\/1.9781611972825.28"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"M. van Leeuwen and A. Siebes. StreamKrimp: Detecting change in data streams. In ECML PKDD, pages\u00a0672\u2013687, 2008.","DOI":"10.1007\/978-3-540-87479-9_62"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"M. van Leeuwen, J. Vreeken, and A. Siebes. Compression picks the item sets that matter. In PKDD, pages\u00a0585\u2013592, 2006.","DOI":"10.1007\/11871637_59"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"M. van Leeuwen, F. Bonchi, B. Sigurbj\u00f6rnsson, and A. Siebes. Compressing tags to find interesting media groups. In CIKM, pages\u00a01147\u20131156, 2009.","DOI":"10.1145\/1645953.1646099"},{"issue":"2","key":"8_CR39","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/s10618-009-0143-4","volume":"19","author":"M. van Leeuwen","year":"2009","unstructured":"M. van Leeuwen, J. Vreeken, and A. Siebes. Identifying the components. Data Min. Knowl. Disc., 19(2):173\u2013292, 2009.","journal-title":"Data Min. Knowl. Disc"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"M. Li and P. Vit\u00e1nyi. An Introduction to Kolmogorov Complexity and its Applications. Springer, 1993.","DOI":"10.1007\/978-1-4757-3860-5"},{"issue":"12","key":"8_CR41","first-page":"3250","volume":"50","author":"M. Li","year":"2004","unstructured":"M. Li, X. Chen, X. Li, B. Ma, and P. Vitanyi. The similarity metric. IEEE TIT, 50(12): 3250\u20133264, 2004.","journal-title":"IEEE TIT"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"C. Lucchese, S. Orlando, and R. Perego. Mining top-k patterns from binary datasets in presence of noise. In SDM, pages\u00a0165\u2013176, 2010.","DOI":"10.1137\/1.9781611972801.15"},{"issue":"1","key":"8_CR43","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1007\/s10618-011-0246-6","volume":"26","author":"M. Mampaey","year":"2013","unstructured":"M. Mampaey and J. Vreeken. Summarising categorical data by clustering attributes. Data Min. Knowl. Disc., 26(1):130\u2013173, 2013.","journal-title":"Data Min. Knowl. Disc"},{"key":"8_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2382577.2382580","volume":"6","author":"M. Mampaey","year":"2012","unstructured":"M. Mampaey, J. Vreeken, and N. Tatti. Summarizing data succinctly with the most informative itemsets. ACM TKDD, 6:1\u201344, 2012.","journal-title":"ACM TKDD"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"P. Miettinen and J. Vreeken. Model order selection for Boolean matrix factorization. In KDD, pages\u00a051\u201359. ACM, 2011.","DOI":"10.1145\/2020408.2020424"},{"key":"8_CR46","unstructured":"P. Miettinen and J. Vreeken. mdl4bmf: Minimum description length for Boolean matrix factorization. ACM TKDD. In Press."},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"S. Papadimitriou, J. Sun, C. Faloutsos, and P. S. Yu. Hierarchical, parameter-free community discovery. In ECML PKDD, pages\u00a0170\u2013187, 2008.","DOI":"10.1007\/978-3-540-87481-2_12"},{"key":"8_CR48","unstructured":"B. Pfahringer. Compression-based feature subset selection. In Proc. IJCAI'95 Workshop on Data Engineering for Inductive Learning, pages\u00a0109\u2013119, 1995."},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"B. A. Prakash, J. Vreeken, and C. Faloutsos. Spotting culprits in epidemics: How many and which ones? In ICDM. IEEE, 2012.","DOI":"10.1109\/ICDM.2012.136"},{"key":"8_CR50","unstructured":"J. Quinlan. C4.5: Programs for Machine Learning. Morgan-Kaufmann, Los Altos, California, 1993."},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"L. D. Raedt. Declarative modeling for machine learning and data mining. In ECML PKDD, pages\u00a02\u20133, 2012.","DOI":"10.1007\/978-3-642-33460-3_2"},{"issue":"1","key":"8_CR52","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1016\/0005-1098(78)90005-5","volume":"14","author":"J. Rissanen","year":"1978","unstructured":"J. Rissanen. Modeling by shortest data description. Automatica, 14(1):465\u2013471, 1978.","journal-title":"Automatica"},{"issue":"2","key":"8_CR53","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1214\/aos\/1176344136","volume":"6","author":"G. Schwarz","year":"1978","unstructured":"G. Schwarz. Estimating the dimension of a model. Annals Stat., 6(2):461\u2013464, 1978.","journal-title":"Annals Stat"},{"issue":"2","key":"8_CR54","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s10115-012-0505-x","volume":"35","author":"H. Shao","year":"2013","unstructured":"H. Shao, B. Tong, and E. Suzuki. Extended MDL principle for feature-based inductive transfer learning. Knowl. Inf. Sys., 35(2):365\u2013389, 2013.","journal-title":"Knowl. Inf. Sys"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"A. Siebes. Queries for data analysis. In IDA, pages\u00a07\u201322, 2012.","DOI":"10.1007\/978-3-642-34156-4_3"},{"key":"8_CR56","doi-asserted-by":"crossref","unstructured":"A. Siebes and R. Kersten. A structure function for transaction data. In SDM, pages\u00a0558\u2013569. SIAM, 2011.","DOI":"10.1137\/1.9781611972818.48"},{"key":"8_CR57","doi-asserted-by":"crossref","unstructured":"A. Siebes, J. Vreeken, and M. van Leeuwen. Item sets that compress. In SDM, pages\u00a0393\u2013404. SIAM, 2006.","DOI":"10.1137\/1.9781611972764.35"},{"key":"8_CR58","doi-asserted-by":"crossref","unstructured":"K. Smets and J. Vreeken. The odd one out: Identifying and characterising anomalies. In SDM, pages\u00a0804\u2013815. SIAM, 2011.","DOI":"10.1137\/1.9781611972818.69"},{"key":"8_CR59","doi-asserted-by":"crossref","unstructured":"K. Smets and J. Vreeken. Slim: Directly mining descriptive patterns. In SDM, pages\u00a0236\u2013247. SIAM, 2012.","DOI":"10.1137\/1.9781611972825.21"},{"key":"8_CR60","doi-asserted-by":"crossref","unstructured":"J. Sun, C. Faloutsos, S. Papadimitriou, and P. S. Yu. Graphscope: parameter-free mining of large time-evolving graphs. In KDD, pages\u00a0687\u2013696, 2007.","DOI":"10.1145\/1281192.1281266"},{"issue":"5","key":"8_CR61","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.ipl.2006.02.003","volume":"98","author":"N. Tatti","year":"2006","unstructured":"N. Tatti. Computational complexity of queries based on itemsets. Inf. Process. Lett., 98(5): 183\u2013187, 2006.","journal-title":"Inf. Process. Lett"},{"key":"8_CR62","doi-asserted-by":"crossref","unstructured":"N. Tatti and J. Vreeken. Finding good itemsets by packing data. In ICDM, pages\u00a0588\u2013597, 2008.","DOI":"10.1109\/ICDM.2008.39"},{"key":"8_CR63","doi-asserted-by":"crossref","unstructured":"N. Tatti and J. Vreeken. Discovering descriptive tile trees by fast mining of optimal geometric subtiles. In ECML PKDD. Springer, 2012.","DOI":"10.1007\/978-3-642-33460-3_6"},{"key":"8_CR64","doi-asserted-by":"crossref","unstructured":"N. Tatti and J. Vreeken. The long and the short of it: Summarizing event sequences with serial episodes. In KDD. ACM, 2012.","DOI":"10.1145\/2339530.2339606"},{"key":"8_CR65","doi-asserted-by":"crossref","unstructured":"J. Vreeken and A. Siebes. Filling in the blanks: Krimp minimisation for missing data. In ICDM, pages\u00a01067\u20131072. IEEE, 2008.","DOI":"10.1109\/ICDM.2008.40"},{"key":"8_CR66","doi-asserted-by":"crossref","unstructured":"J. Vreeken, M. van Leeuwen, and A. Siebes. Characterising the difference. In KDD, pages\u00a0765\u2013774, 2007.","DOI":"10.1145\/1281192.1281274"},{"key":"8_CR67","doi-asserted-by":"crossref","unstructured":"J. Vreeken, M. van Leeuwen, and A. Siebes. Preserving privacy through data generation. In ICDM, pages\u00a0685\u2013690. IEEE, 2007.","DOI":"10.1109\/ICDM.2007.25"},{"issue":"1","key":"8_CR68","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s10618-010-0202-x","volume":"23","author":"J. Vreeken","year":"2011","unstructured":"J. Vreeken, M. van Leeuwen, and A. Siebes. Krimp: Mining itemsets that compress. Data Min. Knowl. Disc., 23(1):169\u2013214, 2011.","journal-title":"Data Min. Knowl. Disc"},{"key":"8_CR69","unstructured":"C. Wallace. Statistical and inductive inference by minimum message length. Springer-Verlag, 2005."},{"key":"8_CR70","doi-asserted-by":"crossref","unstructured":"C. Wang and S. Parthasarathy. Summarizing itemset patterns using probabilistic models. In KDD, pages\u00a0730\u2013735, 2006.","DOI":"10.1145\/1150402.1150495"},{"key":"8_CR71","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1001\/jama.1961.03040290005002","volume":"177","author":"H. Warner","year":"1961","unstructured":"H. Warner, A. Toronto, L. Veasey, and R. Stephenson. A mathematical model for medical diagnosis, application to congenital heart disease. J. Am. Med. Assoc., 177:177\u2013184, 1961.","journal-title":"J. Am. Med. Assoc"}],"container-title":["Frequent Pattern Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-07821-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T01:57:49Z","timestamp":1717293469000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-07821-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319078205","9783319078212"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-07821-2_8","relation":{},"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"30 August 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}