{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T12:18:18Z","timestamp":1764937098663,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T00:00:00Z","timestamp":1564012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shenzhen Basic Research Grant","award":["JCYJ20170816100819428"],"award-info":[{"award-number":["JCYJ20170816100819428"]}]},{"name":"National Natural Science Foundation of China","award":["U1736205, 61603290"],"award-info":[{"award-number":["U1736205, 61603290"]}]},{"name":"Natural Science Basic Research Plan in Shaanxi Province of China","award":["2016JQ6034"],"award-info":[{"award-number":["2016JQ6034"]}]},{"name":"National Key R\\&D Program of China","award":["2018YFC0830500"],"award-info":[{"award-number":["2018YFC0830500"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,7,25]]},"DOI":"10.1145\/3292500.3330825","type":"proceedings-article","created":{"date-parts":[[2019,7,26]],"date-time":"2019-07-26T13:17:26Z","timestamp":1564147046000},"page":"25-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":39,"title":["A Memory-Efficient Sketch Method for Estimating High Similarities in Streaming Sets"],"prefix":"10.1145","author":[{"given":"Pinghui","family":"Wang","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, Shaanxi, China"}]},{"given":"Yiyan","family":"Qi","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, Shaanxi, China"}]},{"given":"Yuanming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, Shaanxi, China"}]},{"given":"Qiaozhu","family":"Zhai","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, Shaanxi, China"}]},{"given":"Chenxu","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Shenzhen, China"}]},{"given":"John C.S.","family":"Lui","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}]},{"given":"Xiaohong","family":"Guan","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University & Tsinghua University, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2019,7,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-018-0074-4"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1999.1690"},{"key":"e_1_3_2_1_3_1","volume-title":"SEQUENCES","author":"Broder A.","year":"1997","unstructured":"A. Broder . On the resemblance and containment of documents . In SEQUENCES , 1997 . A. Broder. On the resemblance and containment of documents. In SEQUENCES, 1997."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557049"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1526709.1526761"},{"key":"e_1_3_2_1_6_1","first-page":"2672","volume-title":"NIPS.","author":"Li Ping","year":"2011","unstructured":"Ping Li , Anshumali Shrivastava , Joshua L. Moore , and Arnd Christian K\u00f6 nig. Hashing algorithms for large-scale learning . In NIPS. , pages 2672 -- 2680 , 2011 . Ping Li, Anshumali Shrivastava, Joshua L. Moore, and Arnd Christian K\u00f6 nig. Hashing algorithms for large-scale learning. In NIPS., pages 2672--2680, 2011."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1326561.1326564"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772759"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2566486.2568017"},{"key":"e_1_3_2_1_10_1","volume-title":"Hyperminhash: Jaccard index sketching in loglog space. CoRR, abs\/1710.08436","author":"Yu Yun William","year":"2017","unstructured":"Yun William Yu and Griffin Weber . Hyperminhash: Jaccard index sketching in loglog space. CoRR, abs\/1710.08436 , 2017 . Yun William Yu and Griffin Weber. Hyperminhash: Jaccard index sketching in loglog space. CoRR, abs\/1710.08436, 2017."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0000(85)90041-8"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/362686.362692"},{"key":"e_1_3_2_1_13_1","first-page":"3122","volume-title":"NIPS","author":"Li Ping","year":"2012","unstructured":"Ping Li , Art B. Owen , and Cun-Hui Zhang . One permutation hashing . In NIPS , pages 3122 -- 3130 , 2012 . Ping Li, Art B. Owen, and Cun-Hui Zhang. One permutation hashing. In NIPS, pages 3122--3130, 2012."},{"key":"e_1_3_2_1_14_1","volume-title":"AOFA","author":"Flajolet Philippe","year":"2007","unstructured":"Philippe Flajolet , Eric Fusy , Olivier Gandouet , and Frederic Meunier . Hyperloglog : The analysis of a near-optimal cardinality estimation algorithm . In AOFA , 2007 . Philippe Flajolet, Eric Fusy, Olivier Gandouet, and Frederic Meunier. Hyperloglog: The analysis of a near-optimal cardinality estimation algorithm. In AOFA, 2007."},{"key":"e_1_3_2_1_15_1","first-page":"732","volume-title":"UAI","author":"Shrivastava Anshumali","year":"2014","unstructured":"Anshumali Shrivastava and Ping Li . Improved densification of one permutation hashing . In UAI , pages 732 -- 741 , 2014 . Anshumali Shrivastava and Ping Li. Improved densification of one permutation hashing. In UAI, pages 732--741, 2014."},{"key":"e_1_3_2_1_16_1","first-page":"557","volume-title":"ICML","author":"Shrivastava Anshumali","year":"2014","unstructured":"Anshumali Shrivastava and Ping Li . Densifying one permutation hashing via rotation for fast near neighbor search . In ICML , pages 557 -- 565 , 2014 . Anshumali Shrivastava and Ping Li. Densifying one permutation hashing via rotation for fast near neighbor search. In ICML, pages 557--565, 2014."},{"key":"e_1_3_2_1_17_1","first-page":"3154","volume-title":"ICML","author":"Shrivastava Anshumali","year":"2017","unstructured":"Anshumali Shrivastava . Optimal densification for fast and accurate minwise hashing . In ICML , pages 3154 -- 3163 , 2017 . Anshumali Shrivastava. Optimal densification for fast and accurate minwise hashing. In ICML, pages 3154--3163, 2017."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"e_1_3_2_1_19_1","volume-title":"June","author":"Manasse Mark","year":"2010","unstructured":"Mark Manasse , Frank McSherry , and Kunal Talwar . Consistent weighted sampling. Technical report , June 2010 . Mark Manasse, Frank McSherry, and Kunal Talwar. Consistent weighted sampling. Technical report, June 2010."},{"key":"e_1_3_2_1_20_1","volume-title":"Consistent weighted sampling made fast, small, and easy. CoRR, abs\/1410.4266","author":"Haeupler Bernhard","year":"2014","unstructured":"Bernhard Haeupler , Mark S. Manasse , and Kunal Talwar . Consistent weighted sampling made fast, small, and easy. CoRR, abs\/1410.4266 , 2014 . Bernhard Haeupler, Mark S. Manasse, and Kunal Talwar. Consistent weighted sampling made fast, small, and easy. CoRR, abs\/1410.4266, 2014."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.80"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783406"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0174"},{"key":"e_1_3_2_1_24_1","first-page":"1498","volume-title":"NIPS","author":"Shrivastava Anshumali","year":"2016","unstructured":"Anshumali Shrivastava . Simple and efficient weighted minwise hashing . In NIPS , pages 1498 -- 1506 , 2016 . Anshumali Shrivastava. Simple and efficient weighted minwise hashing. In NIPS, pages 1498--1506, 2016."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052598"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220089"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/997817.997857"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3225631.3225752"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806515"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/237814.237823"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.64"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/78922.78925"},{"key":"e_1_3_2_1_33_1","first-page":"605","volume-title":"Loglog Counting of Large Cardinalities","author":"Durand Marianne","year":"2003","unstructured":"Marianne Durand and Philippe Flajolet . Loglog Counting of Large Cardinalities , pages 605 -- 617 . Springer Berlin Heidelberg , 2003 . Marianne Durand and Philippe Flajolet. Loglog Counting of Large Cardinalities, pages 605--617. Springer Berlin Heidelberg, 2003."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057088"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dam.2008.06.020"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3097999"}],"event":{"name":"KDD '19: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Anchorage AK USA","acronym":"KDD '19"},"container-title":["Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3292500.3330825","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3292500.3330825","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:26:02Z","timestamp":1750206362000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3292500.3330825"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,25]]},"references-count":36,"alternative-id":["10.1145\/3292500.3330825","10.1145\/3292500"],"URL":"https:\/\/doi.org\/10.1145\/3292500.3330825","relation":{},"subject":[],"published":{"date-parts":[[2019,7,25]]},"assertion":[{"value":"2019-07-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}