{"id":"https://openalex.org/W1963535513","doi":"https://doi.org/10.1145/1281192.1281207","title":"Content-based document routing and index partitioning for scalable similarity-based searches in a large corpus","display_name":"Content-based document routing and index partitioning for scalable similarity-based searches in a large corpus","publication_year":2007,"publication_date":"2007-08-12","ids":{"openalex":"https://openalex.org/W1963535513","doi":"https://doi.org/10.1145/1281192.1281207","mag":"1963535513"},"language":"en","primary_location":{"id":"doi:10.1145/1281192.1281207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058889435","display_name":"Deepavali Bhagwat","orcid":null},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepavali Bhagwat","raw_affiliation_strings":["University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088426443","display_name":"Kave Eshghi","orcid":"https://orcid.org/0000-0003-3374-3145"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kave Eshghi","raw_affiliation_strings":["Hewlett Packard Labs","Hewlett-Packard Labs,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett Packard Labs","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023406554","display_name":"Pankaj Mehra","orcid":"https://orcid.org/0009-0003-3188-243X"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pankaj Mehra","raw_affiliation_strings":["Hewlett Packard Labs","Hewlett-Packard Labs,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett Packard Labs","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1834,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.76046975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.829236626625061},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.757035493850708},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.6225695610046387},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5992771983146667},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5889057517051697},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5614294409751892},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5545663237571716},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4912230372428894},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4200456440448761},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27787503600120544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1989578902721405},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10344606637954712},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07175830006599426},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06986171007156372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.829236626625061},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.757035493850708},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.6225695610046387},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5992771983146667},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5889057517051697},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5614294409751892},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5545663237571716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4912230372428894},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4200456440448761},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27787503600120544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1989578902721405},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10344606637954712},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07175830006599426},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06986171007156372},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1281192.1281207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W89823361","https://openalex.org/W1536854407","https://openalex.org/W1564935865","https://openalex.org/W1570542661","https://openalex.org/W1576397915","https://openalex.org/W1609518033","https://openalex.org/W1956559956","https://openalex.org/W1957582590","https://openalex.org/W1975868314","https://openalex.org/W1992419399","https://openalex.org/W2007842132","https://openalex.org/W2027752285","https://openalex.org/W2028928922","https://openalex.org/W2040058125","https://openalex.org/W2056980397","https://openalex.org/W2081193615","https://openalex.org/W2092433256","https://openalex.org/W2104210894","https://openalex.org/W2121133177","https://openalex.org/W2123482462","https://openalex.org/W2123767107","https://openalex.org/W2132069633","https://openalex.org/W2132627996","https://openalex.org/W2139914326","https://openalex.org/W2140733653","https://openalex.org/W2141641405","https://openalex.org/W2142418251","https://openalex.org/W2147755199","https://openalex.org/W2152565070","https://openalex.org/W2152830316","https://openalex.org/W2156719566","https://openalex.org/W2158049821","https://openalex.org/W2163059190","https://openalex.org/W2167898414","https://openalex.org/W2325227998","https://openalex.org/W2939083804","https://openalex.org/W4236944670","https://openalex.org/W6632163548","https://openalex.org/W6634059332","https://openalex.org/W6634463810","https://openalex.org/W6636190696","https://openalex.org/W6640862754"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2357523926"],"abstract_inverted_index":{"We":[0,19],"present":[1],"a":[2,16,88,95,115],"document":[3,89,138],"routing":[4],"and":[5,83,126,148],"index":[6,69],"partitioning":[7],"scheme":[8],"for":[9,149],"scalable":[10,82],"similarity-based":[11,24,111],"search":[12,25,85,152],"of":[13,49,98,106,118,136,162],"documents":[14,30,52],"in":[15,34,53],"large":[17],"corpus.":[18],"consider":[20],"the":[21,37,47,51,67,93,104,107,134,137,160,163],"case":[22],"when":[23],"is":[26,42,64,90,124,156],"performed":[27],"by":[28],"finding":[29],"that":[31,74],"have":[32],"features":[33,48,105,135,161],"common":[35],"with":[36],"query":[38,154],"document.":[39,108,164],"While":[40],"it":[41],"possible":[43],"to":[44,65,102,131,142],"store":[45,103],"all":[46,50],"one":[54],"index,":[55],"this":[56],"suffers":[57],"from":[58],"obvious":[59],"scalability":[60],"problems.":[61],"Our":[62,122],"approach":[63,123],"partition":[66],"feature":[68],"into":[70,92],"multiple":[71],"smaller":[72],"partitions":[73,99,119,133],"can":[75],"be":[76,140],"hosted":[77],"on":[78,159],"separate":[79],"servers,":[80],"enabling":[81],"parallel":[84],"execution.":[86],"When":[87],"ingested":[91],"repository,":[94],"small":[96,116],"number":[97,117],"are":[100,120],"chosen":[101],"To":[109],"perform":[110],"search,":[112],"also,":[113],"only":[114],"queried.":[121],"stateless":[125],"incremental.":[127],"The":[128],"decision":[129],"as":[130],"which":[132],"should":[139],"routed":[141],"(for":[143],"storing":[144],"at":[145,153],"ingestion":[146],"time,":[147],"similarity":[150],"based":[151,158],"time)":[155],"solely":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}