{"id":"https://openalex.org/W2495231312","doi":"https://doi.org/10.1109/snpd.2016.7515917","title":"Accelerated diffusion-based recommendation algorithm on tripartite graphs with GPU clusters","display_name":"Accelerated diffusion-based recommendation algorithm on tripartite graphs with GPU clusters","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2495231312","doi":"https://doi.org/10.1109/snpd.2016.7515917","mag":"2495231312"},"language":"en","primary_location":{"id":"doi:10.1109/snpd.2016.7515917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd.2016.7515917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","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/A5082413846","display_name":"Mi Li","orcid":"https://orcid.org/0000-0001-7523-1266"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mi Li","raw_affiliation_strings":["School of Software Engineering, Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048299480","display_name":"Jie Huang","orcid":"https://orcid.org/0000-0003-1570-6797"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Huang","raw_affiliation_strings":["School of Software Engineering, Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110873607","display_name":"Jingpeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingpeng Wang","raw_affiliation_strings":["School of Software Engineering, Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"307","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"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/T11478","display_name":"Caching and Content Delivery","score":0.9991000294685364,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9896000027656555,"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/speedup","display_name":"Speedup","score":0.93202805519104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8791171312332153},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7535402774810791},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.613932728767395},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5855430364608765},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.44895139336586},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43712273240089417}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.93202805519104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8791171312332153},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7535402774810791},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.613932728767395},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5855430364608765},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.44895139336586},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43712273240089417},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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:10.1109/snpd.2016.7515917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd.2016.7515917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.4000000059604645,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1893639437","https://openalex.org/W1973987653","https://openalex.org/W2030319410","https://openalex.org/W2108157916","https://openalex.org/W2142281120","https://openalex.org/W2166237624","https://openalex.org/W2341865734","https://openalex.org/W4253315077"],"related_works":["https://openalex.org/W2983282793","https://openalex.org/W2317245370","https://openalex.org/W198851386","https://openalex.org/W1980160788","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W2148915962","https://openalex.org/W4313433561","https://openalex.org/W2283866686","https://openalex.org/W2948365806"],"abstract_inverted_index":{"Exorbitant":[0],"computation":[1],"cost":[2,131],"hinders":[3],"the":[4,53,56,62,96,104,115,129,149,159,164,167,200,210,237],"practical":[5],"application":[6,13],"of":[7,37,55,67,119,140,166,190,202,209,212,216,222],"recommendation":[8,19,69],"algorithm,":[9],"especially":[10],"in":[11],"time-critical":[12],"scenario.":[14],"Although":[15],"experiments":[16],"show":[17],"that":[18,231],"algorithm":[20,74,97,168,224],"based":[21],"on":[22,26,70,99,112,122,132,138,158,174,188,225],"an":[23],"integrated":[24],"diffusion":[25],"user-item-tag":[27],"tripartite":[28,72],"graphs":[29,73],"can":[30,108,234],"significantly":[31],"improve":[32,52,236],"accuracy,":[33],"diversification":[34],"and":[35,65,81,90,143,219],"novelty":[36],"recommendation,":[38],"it":[39],"is":[40,48,205],"also":[41,206],"very":[42],"time-consuming.":[43],"Therefore,":[44],"a":[45,100,180],"parallel":[46,63],"solution":[47],"frequently":[49],"needed":[50],"to":[51,95,179],"performance":[54,151,165],"algorithm.":[57],"This":[58],"paper":[59],"explicitly":[60],"presents":[61],"implementation":[64],"optimizations":[66],"diffusion-based":[68],"weighted":[71],"using":[75],"Compute":[76],"Unified":[77],"Device":[78],"Architecture":[79],"(CUDA)":[80],"related":[82],"optimization":[83],"solutions":[84],"including":[85],"shared":[86,126],"memory,":[87],"stream":[88],"scheduling":[89],"GPU":[91,106,175,182,203,232],"cluster":[92],"optimization.":[93],"Compared":[94],"running":[98],"single":[101,181],"CPU":[102,214,227],"core,":[103],"unoptimized":[105],"kernel":[107],"achieve":[109,185],"153.9":[110],"speedup":[111,187,201,211],"average":[113],"with":[114,144,169],"input":[116],"dataset":[117,139],"consists":[118],"30000":[120],"records":[121,142],"GTX":[123],"980.":[124],"With":[125],"memory":[127,133],"applied,":[128],"time":[130],"access":[134],"saves":[135],"about":[136,153],"50%":[137],"90000":[141],"2":[145],"way":[146],"streams":[147],"scheduling,":[148],"kernel's":[150],"improves":[152],"7%":[154],"~":[155],"13%.":[156],"Based":[157],"optimized":[160],"kernel,":[161],"we":[162,184],"evaluate":[163],"customized":[170],"socket":[171],"communication":[172],"mechanism":[173],"clusters.":[176],"And":[177],"compared":[178],"node,":[183],"7.55":[186],"clusters":[189,204,215],"9":[191,217],"GPUs":[192],"when":[193],"recommending":[194],"for":[195],"8000":[196],"users.":[197],"Besides":[198],"this,":[199],"26.1":[207],"times":[208,221],"our":[213],"nodes":[218],"1586.28":[220],"serial":[223],"one":[226],"core.":[228],"It":[229],"proves":[230],"technology":[233],"dramatically":[235],"algorithm's":[238],"performance.":[239]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}