{"id":"https://openalex.org/W2152526152","doi":"https://doi.org/10.1145/2433396.2433422","title":"Optimizing parallel algorithms for all pairs similarity search","display_name":"Optimizing parallel algorithms for all pairs similarity search","publication_year":2013,"publication_date":"2013-02-04","ids":{"openalex":"https://openalex.org/W2152526152","doi":"https://doi.org/10.1145/2433396.2433422","mag":"2152526152"},"language":"en","primary_location":{"id":"doi:10.1145/2433396.2433422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2433396.2433422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},"type":"article","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/A5049850277","display_name":"Maha Alabduljalil","orcid":"https://orcid.org/0000-0001-7083-8675"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maha Ahmed Alabduljalil","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024587620","display_name":"Xun Tang","orcid":"https://orcid.org/0000-0002-6990-0168"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xun Tang","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060730782","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0003-1902-3387"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049850277"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":5.7881,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96650332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"203","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7971048355102539},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7202750444412231},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.666257381439209},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5786986351013184},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.5662598013877869},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5351753234863281},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.49662429094314575},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4921643137931824},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48550915718078613},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4758301079273224},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.41447779536247253},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.377011239528656},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3540155291557312},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32997679710388184},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.14597803354263306},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13548094034194946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13240265846252441},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11356031894683838}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971048355102539},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7202750444412231},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.666257381439209},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5786986351013184},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.5662598013877869},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5351753234863281},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.49662429094314575},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4921643137931824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48550915718078613},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4758301079273224},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.41447779536247253},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.377011239528656},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3540155291557312},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32997679710388184},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.14597803354263306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13548094034194946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13240265846252441},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11356031894683838},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2433396.2433422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2433396.2433422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.9979","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.9979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucsb.edu/~tyang/papers/wsdm2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322668","display_name":"Kuwait University","ror":"https://ror.org/021e5j056"},{"id":"https://openalex.org/F4320337367","display_name":"Division of Materials Research","ror":"https://ror.org/01pc7k308"},{"id":"https://openalex.org/F4320337965","display_name":"California NanoSystems Institute","ror":"https://ror.org/00q7fqf35"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W1660390307","https://openalex.org/W1956559956","https://openalex.org/W1981053739","https://openalex.org/W1997657677","https://openalex.org/W2047756776","https://openalex.org/W2062028408","https://openalex.org/W2067432306","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2099194763","https://openalex.org/W2110166424","https://openalex.org/W2117350857","https://openalex.org/W2137139422","https://openalex.org/W2138662031","https://openalex.org/W2151930506","https://openalex.org/W2153180170","https://openalex.org/W2154461554","https://openalex.org/W2161443453","https://openalex.org/W2171960770","https://openalex.org/W2173213060","https://openalex.org/W2298843527","https://openalex.org/W2331485624","https://openalex.org/W6629956336"],"related_works":["https://openalex.org/W2413339343","https://openalex.org/W1569389315","https://openalex.org/W2023309578","https://openalex.org/W2503642292","https://openalex.org/W2794587399","https://openalex.org/W2013685631","https://openalex.org/W3120511008","https://openalex.org/W2980679393","https://openalex.org/W2401320555","https://openalex.org/W2017267929"],"abstract_inverted_index":{"All":[0],"pairs":[1],"similarity":[2],"search":[3,9],"is":[4],"used":[5,17],"in":[6,91],"many":[7],"web":[8],"and":[10,22,77,105,124],"data":[11,43,97,125],"mining":[12],"applications.":[13],"Previous":[14],"work":[15],"has":[16],"comparison":[18,80,89],"filtering,":[19],"inverted":[20,106],"indexing,":[21],"parallel":[23,129],"accumulation":[24],"of":[25,103,121,140],"partial":[26],"intermediate":[27,35],"results":[28,36,110],"to":[29,117],"expedite":[30],"its":[31],"execution.":[32],"However,":[33],"shuffling":[34],"can":[37],"incur":[38],"significant":[39],"communication":[40,126],"overhead":[41],"as":[42],"scales":[44],"up.":[45],"This":[46],"paper":[47],"studies":[48],"a":[49,66,83,95,132],"scalable":[50],"two-step":[51],"approach":[52,115],"called":[53],"Partition-based":[54],"Similarity":[55],"Search":[56],"(PSS)":[57],"which":[58],"incorporates":[59],"several":[60],"optimization":[61],"techniques.":[62],"First,":[63],"PSS":[64,87],"uses":[65],"static":[67],"partitioning":[68],"algorithm":[69],"that":[70,99,112],"places":[71],"dissimilar":[72],"vectors":[73],"into":[74],"different":[75],"groups":[76],"balance":[78],"the":[79,101,113],"workload":[81],"with":[82,144],"circular":[84],"assignment.":[85],"Second,":[86],"executes":[88],"tasks":[90],"parallel,":[92],"each":[93],"using":[94],"hybrid":[96],"structure":[98],"combines":[100],"advantages":[102],"forward":[104],"indexing.":[107],"Our":[108],"evaluation":[109],"show":[111],"proposed":[114],"leads":[116],"an":[118,138],"early":[119],"elimination":[120],"unnecessary":[122],"I/O":[123],"while":[127],"sustaining":[128],"efficiency.":[130],"As":[131],"result,":[133],"it":[134],"improves":[135],"performance":[136],"by":[137],"order":[139],"magnitude":[141],"when":[142],"dealing":[143],"large":[145],"datasets.":[146]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}