{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:38:26Z","timestamp":1740123506520,"version":"3.37.3"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2016,2,6]],"date-time":"2016-02-06T00:00:00Z","timestamp":1454716800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (CN)","doi-asserted-by":"publisher","award":["61173160"],"award-info":[{"award-number":["61173160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010829","name":"Scientific Research Program of the Higher Education Institution of XinJiang","doi-asserted-by":"crossref","award":["XJEDU2014S087"],"award-info":[{"award-number":["XJEDU2014S087"]}],"id":[{"id":"10.13039\/501100010829","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1007\/s11227-016-1651-9","type":"journal-article","created":{"date-parts":[[2016,2,6]],"date-time":"2016-02-06T10:28:40Z","timestamp":1454754520000},"page":"1179-1200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["An efficient MapReduce algorithm for similarity join in metric spaces"],"prefix":"10.1007","volume":"72","author":[{"given":"Wen","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanming","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,2,6]]},"reference":[{"key":"1651_CR1","doi-asserted-by":"crossref","unstructured":"Henzinger MR (2006) Finding near-duplicate web pages: a large-scale evaluation of algorithms. In: Proceedings of the 29th annual international ACM SIGIR conference on research and development in information retrieval, pp 284\u2013291","DOI":"10.1145\/1148170.1148222"},{"key":"1651_CR2","doi-asserted-by":"crossref","unstructured":"Broder AZ, Glassman SC, Manasse MS, Zweig G (1997) Syntactic clustering of the web. Comput Netw 29(813):1157\u20131166","DOI":"10.1016\/S0169-7552(97)00031-7"},{"issue":"1","key":"1651_CR3","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean J, Ghemawat S (2008) Mapreduce: simplified data processing on large clusters. Commun ACM 51(1):107\u2013113","journal-title":"Commun ACM"},{"issue":"8","key":"1651_CR4","doi-asserted-by":"crossref","first-page":"704","DOI":"10.14778\/2212351.2212353","volume":"5","author":"A Metwally","year":"2012","unstructured":"Metwally A, Faloutsos C (2012) V-smart-join: a scalable mapreduce framework for all-pair similarity joins of multisets and vectors. Proc VLDB Endow 5(8):704\u2013715","journal-title":"Proc VLDB Endow"},{"issue":"12","key":"1651_CR5","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.14778\/2732977.2732981","volume":"7","author":"AD Sarma","year":"2014","unstructured":"Sarma AD, He Y, Chaudhuri S (2014) Clusterjoin: a similarity joins framework using map-reduce. Proc VLDB Endow 7(12):1059\u20131070","journal-title":"Proc VLDB Endow"},{"issue":"1","key":"1651_CR6","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/69.979979","volume":"14","author":"K Shim","year":"2002","unstructured":"Shim K, Srikant R, Agrawal R (2002) High-dimensional similarity joins. IEEE Trans Knowl Data Eng 14(1):156\u2013171","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1651_CR7","doi-asserted-by":"crossref","unstructured":"Wang Y, Metwally A, Parthasarathy S (2013) Scalable all-pairs similarity search in metric spaces. In: Proceedings of the 19th ACM SIGKDD international conference on knowledge discovery and data mining, pp 829\u2013837","DOI":"10.1145\/2487575.2487625"},{"key":"1651_CR8","unstructured":"Weber R, Schek H-J, Blott S (1998) A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces. In: Proceedings of the VLDB conference, pp 194\u2013205"},{"key":"1651_CR9","doi-asserted-by":"crossref","unstructured":"Bingham E, Mannila H (2001) Random projection in dimensionality reduction: applications to image and text data. In: Knowledge discovery and data mining, pp 245\u2013250","DOI":"10.1145\/502512.502546"},{"issue":"2","key":"1651_CR10","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1145\/253262.253332","volume":"26","author":"F Korn","year":"1997","unstructured":"Korn F, Jagadish HV, Faloutsos C (1997) Efficiently supporting ad hoc queries in large datasets of time sequences. ACM SIGMOD 26(2):289\u2013300","journal-title":"ACM SIGMOD"},{"issue":"2","key":"1651_CR11","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1145\/568518.568520","volume":"27","author":"K Chakrabarti","year":"2002","unstructured":"Chakrabarti K, Keogh EJ, Mehrotra S, Pazzani MJ (2002) Locally adaptive dimensionality reduction for indexing large time series databases. ACM Trans Database Syst 27(2):188\u2013228","journal-title":"ACM Trans Database Syst"},{"key":"1651_CR12","unstructured":"Keogh EJ, Pazzani MJ (2000) A simple dimensionality reduction technique for fast similarity search in large time series databases. Knowl Discov Data Min Curr Issues New Appl 122\u2013133"},{"key":"1651_CR13","doi-asserted-by":"crossref","unstructured":"Vernica R, Carey MJ, Li C (2010) Efficient parallel set-similarity joins using mapreduce. In: Proceedings of the 2010 ACM SIGMOD international conference on management of data, pp 495\u2013506","DOI":"10.1145\/1807167.1807222"},{"key":"1651_CR14","doi-asserted-by":"crossref","unstructured":"Chaudhuri S, Ganti V, Kaushik R (2006) A primitive operator for similarity joins in data cleaning. In: ICDE\u201906. Proceedings of the 22nd international conference on data engineering, p\u00a05","DOI":"10.1109\/ICDE.2006.9"},{"issue":"3","key":"1651_CR15","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1145\/2000824.2000825","volume":"36","author":"C Xiao","year":"2011","unstructured":"Xiao C, Wang W, Lin X, Yu JX, Wang G (2011) Efficient similarity joins for near-duplicate detection. ACM Trans Database Syst (TODS) 36(3):15","journal-title":"ACM Trans Database Syst (TODS)"},{"key":"1651_CR16","doi-asserted-by":"crossref","unstructured":"Okcan A, Riedewald M (2011) Processing theta-joins using mapreduce. In: SIGMOD, pp 949\u2013960","DOI":"10.1145\/1989323.1989423"},{"key":"1651_CR17","doi-asserted-by":"crossref","unstructured":"Beyer Kevin S, Goldstein J, Ramakrishnan R, Shaft U (1999) When is \u201cnearest neighbor\u201d meaningful? In: Proceedings of the ICDT, pp 217\u2013235","DOI":"10.1007\/3-540-49257-7_15"},{"key":"1651_CR18","doi-asserted-by":"crossref","DOI":"10.1017\/9781139171854","volume-title":"Metric spaces: iteration and application","author":"V Bryant","year":"1985","unstructured":"Bryant V (1985) Metric spaces: iteration and application. cambridge University Press, Cambridge"},{"issue":"4","key":"1651_CR19","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1007\/s00778-005-0178-0","volume":"16","author":"C Traina Jr","year":"2007","unstructured":"Traina C Jr, Santos Filho RF, Traina AJM, Vieira MR, Faloutsos Christos (2007) The omni-family of all-purpose access methods: a simple and effective way to make similarity search more efficient. VLDB J 16(4):483\u2013505","journal-title":"VLDB J"},{"key":"1651_CR20","doi-asserted-by":"crossref","unstructured":"Chen L, Gao Y, Li X, Jensen CS, Chen G (2015) Efficient metric indexing for similarity search. In: International conference on data engineering (ICDE)","DOI":"10.1109\/ICDE.2015.7113317"},{"key":"1651_CR21","doi-asserted-by":"crossref","unstructured":"Yang S, Yan X, Zong B, Khan A (2012) Towards effective partition management for large graphs. In: SIGMOD","DOI":"10.1145\/2213836.2213895"},{"key":"1651_CR22","doi-asserted-by":"crossref","unstructured":"Bourse F, Lelarge M, Vojnovic M (2014) Balanced graph edge partition. In: KDD \u201914\u201420th ACM SIGKDD international conference on knowledge discovery and data mining, pp 1456\u20131465","DOI":"10.1145\/2623330.2623660"},{"issue":"2","key":"1651_CR23","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/BF02854581","volume":"9","author":"F Harary","year":"1960","unstructured":"Harary F, Norman RZ (1960) Some properties of line digraphs. Rend Circ Mat Palermo 9(2):161\u2013168","journal-title":"Rend Circ Mat Palermo"},{"key":"1651_CR24","doi-asserted-by":"crossref","unstructured":"Fiduccia CM, Mattheyses RM (1982) A linear-time heuristic for improving network partitions. In: 19th Proceedings of the design automation conference, pp 175\u2013181","DOI":"10.1109\/DAC.1982.1585498"},{"key":"1651_CR25","unstructured":"Newman DJ, Asuncion A (2007) UCI machine learning repository. http:\/\/mlearn.ics.uci.edu\/MLRepository.html . Accessed 26 Dec 2015"},{"key":"1651_CR26","unstructured":"Wikipedia. https:\/\/en.wikipedia.org\/wiki\/Main_Page . Accessed 28 Dec 2015"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1651-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-016-1651-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1651-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,16]],"date-time":"2020-05-16T12:34:02Z","timestamp":1589632442000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-016-1651-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,2,6]]},"references-count":26,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,3]]}},"alternative-id":["1651"],"URL":"https:\/\/doi.org\/10.1007\/s11227-016-1651-9","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2016,2,6]]}}}