{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,2]],"date-time":"2023-09-02T13:11:00Z","timestamp":1693660260074},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2015,5,22]],"date-time":"2015-05-22T00:00:00Z","timestamp":1432252800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1007\/s10844-015-0363-6","type":"journal-article","created":{"date-parts":[[2015,5,21]],"date-time":"2015-05-21T06:06:45Z","timestamp":1432188405000},"page":"473-497","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Fast and scalable vector similarity joins with MapReduce"],"prefix":"10.1007","volume":"46","author":[{"given":"Byoungju","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyun Joon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junho","family":"Shim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongjoo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sang-goo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,5,22]]},"reference":[{"key":"363_CR1","doi-asserted-by":"crossref","unstructured":"Baraglia, R., De Francisci Morales, G., & Lucchese, C. (2010). Document similarity self-join with mapreduce. In Proceedings of the 2010 IEEE International Conference on Data Mining, ICDM \u201910, pp. 731\u2013736. doi: 10.1109\/ICDM.2010.70 .","DOI":"10.1109\/ICDM.2010.70"},{"key":"363_CR2","doi-asserted-by":"crossref","unstructured":"Bayardo, R.J., Ma, Y., & Srikant, R. (2007). Scaling up all pairs similarity search. In Proceedings of the 16th international conference on World Wide Web, WWW \u201907, pp. 131\u2013140. doi: 10.1145\/1242572.1242591 . New York: ACM.","DOI":"10.1145\/1242572.1242591"},{"key":"363_CR3","doi-asserted-by":"crossref","unstructured":"Blanas, S., Patel, J.M., Ercegovac, V., Rao, J., Shekita, E.J., & Tian, Y. (2010). A comparison of join algorithms for log processing in mapreduce. In Proceedings of the 2010 ACM SIGMOD international conference on Management of data, SIGMOD \u201910, pp. 975\u2013986.","DOI":"10.1145\/1807167.1807273"},{"issue":"2","key":"363_CR4","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1023\/A:1016515829761","volume":"19","author":"C B\u00f6hm","year":"2002","unstructured":"B\u00f6hm, C., Kriegel, H.P., & Seidl, T. (2002). Combining approximation techniques and vector quantization for adaptable similarity search. Journal of Intelligent Information System, 19(2), 207\u2013230.","journal-title":"Journal of Intelligent Information System"},{"key":"363_CR5","doi-asserted-by":"crossref","unstructured":"Chakrabarti, K., Chaudhuri, S., Ganti, V., & Xin, D. (2008). An efficient filter for approximate membership checking. In SIGMOD \u201908, pp. 805\u2013818.","DOI":"10.1145\/1376616.1376697"},{"key":"363_CR6","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganti, V., & Kaushik, R. (2006). A primitive operator for similarity joins in data cleaning. In Proceedings of the 22nd International Conference on Data Engineering, ICDE \u201906, pp. 5. doi: 10.1109\/ICDE.2006.9 .","DOI":"10.1109\/ICDE.2006.9"},{"key":"363_CR7","doi-asserted-by":"crossref","unstructured":"Conrad, J.G., Guo, X.S., & Schriber, C.P. (2003). Online duplicate document detection: signature reliability in a dynamic retrieval environment. In Proceedings of the 12th international conference on Information and knowledge management, CIKM \u201903, pp. 443\u2013452. doi: 10.1145\/956863.956946 .","DOI":"10.1145\/956863.956946"},{"issue":"1","key":"363_CR8","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. Communications of the ACM, 51(1), 107\u2013113. doi: 10.1145\/1327452.1327492 .","journal-title":"Communications of the ACM"},{"key":"363_CR9","doi-asserted-by":"crossref","unstructured":"Dooms, S., Audenaert, P., Fostier, J., Pessemier, T.D., & Martens, L. (2013). In-memory, distributed content-based recommender system. Journal of Intelligent Information System. doi: 10.1007\/s10844-013-0276-1 .","DOI":"10.1007\/s10844-013-0276-1"},{"key":"363_CR10","unstructured":"GroupLens (2011). Movielens data sets, grouplens research. http:\/\/www.grouplens.org\/node\/73 ."},{"key":"363_CR11","doi-asserted-by":"crossref","unstructured":"Henzinger, M. (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, SIGIR \u201906, pp. 284\u2013291. doi: 10.1145\/1148170.1148222 .","DOI":"10.1145\/1148170.1148222"},{"key":"363_CR12","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1145\/1721654.1721677","volume":"4","author":"Y Koren","year":"2010","unstructured":"Koren, Y. (2010). Collaborative filtering with temporal dynamics. Communications of the ACM, 4, 89\u201397. doi: 10.1145\/1721654.1721677 .","journal-title":"Communications of the ACM"},{"key":"363_CR13","unstructured":"Lee, D. (2011). An efficient filtering framework for vector similarity joins. Ph.D. thesis, Seoul National University, Seoul, South Korea."},{"key":"363_CR14","doi-asserted-by":"crossref","unstructured":"Lee, D., Park, J., Shim, J., & Lee, S.g. (2010). An efficient similarity join algorithm with cosine similarity predicate. In Proceedings of the 21st International Conference on Database and Expert Systems Applications: Part II, DEXA\u201910, pp. 422\u2013436. Berlin: Springer. http:\/\/dl.acm.org\/citation.cfm?id=1887568.1887611 .","DOI":"10.1007\/978-3-642-15251-1_33"},{"key":"363_CR15","unstructured":"Leskovec, J. (2012). Stanford network analysis project. http:\/\/snap.stanford.edu\/ ."},{"issue":"2","key":"363_CR16","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91\u2013110. doi: 10.1023\/B:VISI.0000029664.99615.94 .","journal-title":"International Journal of Computer Vision"},{"issue":"8","key":"363_CR17","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. Proceedings of the VLDB Endow, 5(8), 704\u2013715. http:\/\/dl.acm.org\/citation.cfm?id=2212351.2212353 .","journal-title":"Proceedings of the VLDB Endow"},{"key":"363_CR18","doi-asserted-by":"crossref","unstructured":"Nist\u00e9r, D., & Stew\u00e9nius, H. (2006). Scalable recognition with a vocabulary tree. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 2161\u20132168.","DOI":"10.1109\/CVPR.2006.264"},{"issue":"1","key":"363_CR19","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.is.2010.07.003","volume":"36","author":"LA Ribeiro","year":"2011","unstructured":"Ribeiro, L.A., & Harder, T. (2011). Generalizing prefix filtering to improve set similarity joins. Information Systems, 36(1), 62\u201378. doi: 10.1016\/j.is.2010.07.003 . http:\/\/www.sciencedirect.com\/science\/article\/B6V0G-50GMMMG-3\/2\/f121cda9a0ee1ff6738138a90ff2d488 .","journal-title":"Information Systems"},{"key":"363_CR20","doi-asserted-by":"crossref","unstructured":"Ruan, J., & Zhang, W. (2007). An efficient spectral algorithm for network community discovery and its applications to biological and social networks. In Seventh IEEE International Conference on Data Mining, ICDM 2007, pp. 643\u2013648: IEEE.","DOI":"10.1109\/ICDM.2007.72"},{"key":"363_CR21","doi-asserted-by":"crossref","unstructured":"Satuluri, V., & Parthasarathy, S. (2009). Scalable graph clustering using stochastic flows: applications to community discovery. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, KDD \u201909, pp. 737\u2013746. doi: 10.1145\/1557019.1557101 . New York: ACM.","DOI":"10.1145\/1557019.1557101"},{"key":"363_CR22","first-page":"4:2","volume":"2009","author":"X Su","year":"2009","unstructured":"Su, X., & Khoshgoftaar, T.M. (2009). A survey of collaborative filtering techniques. Advanced Artificial Intelligence, 2009, 4:2\u20134:2. doi: 10.1155\/2009\/421425 .","journal-title":"Advanced Artificial Intelligence"},{"key":"363_CR23","doi-asserted-by":"crossref","unstructured":"Vernica, R., Carey, M.J., & Li, C. (2010). Efficient parallel set-similarity joins using mapreduce. In Proceedings of the 2010 ACM SIGMOD International Conference on Management of data, SIGMOD \u201910, pp. 495\u2013506. doi: 10.1145\/1807167.1807222 . New York: ACM.","DOI":"10.1145\/1807167.1807222"},{"issue":"3","key":"363_CR24","doi-asserted-by":"crossref","first-page":"15:1","DOI":"10.1145\/2000824.2000825","volume":"36","author":"C Xiao","year":"2011","unstructured":"Xiao, C., Wang, W., Lin, X., Yu, J.X., & Wang, G. (2011). Efficient similarity joins for near-duplicate detection. ACM Transactions on Database Systems, 36(3), 15:1\u201315:41. doi: 10.1145\/2000824.2000825 .","journal-title":"ACM Transactions on Database Systems"},{"key":"363_CR25","doi-asserted-by":"crossref","unstructured":"Yang, B., Myung, J., Lee, S.g., & Lee, D. (2013). A mapreduce-based filtering algorithm for vector similarity join. In Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication, ICUIMC \u201913, pp. 71:1\u201371:5. doi: 10.1145\/2448556.2448627 . New York: ACM.","DOI":"10.1145\/2448556.2448627"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-015-0363-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10844-015-0363-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-015-0363-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T02:10:54Z","timestamp":1559268654000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10844-015-0363-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5,22]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,6]]}},"alternative-id":["363"],"URL":"https:\/\/doi.org\/10.1007\/s10844-015-0363-6","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,5,22]]}}}