{"id":"https://openalex.org/W2512066066","doi":"https://doi.org/10.1109/infcomw.2016.7562179","title":"Shuffle-efficient distributed Locality Sensitive Hashing on spark","display_name":"Shuffle-efficient distributed Locality Sensitive Hashing on spark","publication_year":2016,"publication_date":"2016-04-01","ids":{"openalex":"https://openalex.org/W2512066066","doi":"https://doi.org/10.1109/infcomw.2016.7562179","mag":"2512066066"},"language":"en","primary_location":{"id":"doi:10.1109/infcomw.2016.7562179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcomw.2016.7562179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","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/A5069774066","display_name":"Wanxin Zhang","orcid":"https://orcid.org/0000-0002-1943-5931"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanxin Zhang","raw_affiliation_strings":["National Lab for Parallel and Distributed Processing, College of Computer National University of Defense Technology, Changsha, Hunan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Lab for Parallel and Distributed Processing, College of Computer National University of Defense Technology, Changsha, Hunan","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["National Lab for Parallel and Distributed Processing, College of Computer National University of Defense Technology, Changsha, Hunan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Lab for Parallel and Distributed Processing, College of Computer National University of Defense Technology, Changsha, Hunan","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652475","display_name":"Ying Xu","orcid":"https://orcid.org/0000-0002-3972-4669"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Xu","raw_affiliation_strings":["National Lab for Parallel and Distributed Processing, College of Computer National University of Defense Technology, Changsha, Hunan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Lab for Parallel and Distributed Processing, College of Computer National University of Defense Technology, Changsha, Hunan","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395351","display_name":"Yiming Zhang","orcid":"https://orcid.org/0000-0001-6450-8485"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Zhang","raw_affiliation_strings":["National Lab for Parallel and Distributed Processing, College of Computer National University of Defense Technology, Changsha, Hunan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Lab for Parallel and Distributed Processing, College of Computer National University of Defense Technology, Changsha, Hunan","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"766","last_page":"767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13270","display_name":"QR Code Applications and Technologies","score":0.970300018787384,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7195605039596558},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7010115385055542},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.6459661722183228},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6287329196929932},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.560783326625824},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.34343937039375305},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3380146026611328},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.16743114590644836},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07573887705802917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7195605039596558},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7010115385055542},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6459661722183228},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6287329196929932},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.560783326625824},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.34343937039375305},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3380146026611328},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.16743114590644836},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07573887705802917},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infcomw.2016.7562179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcomw.2016.7562179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W2131975293","https://openalex.org/W2162006472"],"related_works":["https://openalex.org/W2000601968","https://openalex.org/W2135779989","https://openalex.org/W1835589799","https://openalex.org/W2144265691","https://openalex.org/W2033383639","https://openalex.org/W2754607325","https://openalex.org/W3108918257","https://openalex.org/W144856782","https://openalex.org/W2080135560","https://openalex.org/W3016124764"],"abstract_inverted_index":{"Locality":[0],"Sensitive":[1],"Hashing":[2],"(LSH)":[3],"is":[4,22,45],"an":[5],"important":[6],"indexing":[7,59],"technique":[8],"for":[9,61],"approximate":[10],"similarity":[11],"search":[12],"in":[13],"high-dimensional":[14],"spaces.":[15],"An":[16],"obvious":[17],"limitation":[18],"of":[19,25,40],"LSH":[20,41],"approaches":[21],"the":[23,62,67,72,77,90,96,101,108],"lack":[24],"capability":[26],"and":[27,70,106],"scalability":[28],"to":[29,88],"deal":[30],"with":[31],"massive":[32],"data.":[33],"This":[34],"paper":[35],"proposes":[36],"a":[37,50,57,84],"distributed":[38,52],"variant":[39],"called":[42],"Spark-LSH,":[43,63],"which":[44,64],"implemented":[46],"on":[47],"Apache":[48],"Spark,":[49],"well-known":[51],"computing":[53],"framework.":[54],"We":[55],"design":[56],"shuffle-efficient":[58],"scheme":[60,87,98],"can":[65,99],"reduce":[66,100],"data":[68],"shuffle":[69,103],"improve":[71,89],"network":[73,102],"efficiency":[74],"when":[75],"constructing":[76],"hash":[78],"table":[79],"indices.":[80],"Furthermore,":[81],"we":[82],"propose":[83],"location-aware":[85],"querying":[86],"query":[91,109],"performance.":[92],"Experiments":[93],"show":[94],"that":[95],"Spark-LSH":[97],"overhead":[104],"remarkably":[105],"accelerate":[107],"significantly.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
