{"id":"https://openalex.org/W4385585441","doi":"https://doi.org/10.1109/ipdpsw59300.2023.00042","title":"Optimizing Irregular Dense Operators of Heterogeneous GNN Models on GPU","display_name":"Optimizing Irregular Dense Operators of Heterogeneous GNN Models on GPU","publication_year":2023,"publication_date":"2023-05-01","ids":{"openalex":"https://openalex.org/W4385585441","doi":"https://doi.org/10.1109/ipdpsw59300.2023.00042"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw59300.2023.00042","doi":"https://doi.org/10.1109/ipdpsw59300.2023.00042","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ipdpsw59300.2023.00042","pdf_url":null,"source":{"id":"https://openalex.org/S4393918253","display_name":"IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","issn_l":"2164-7062","issn":["2164-7062"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5063948428","display_name":"Israt Nisa","orcid":"https://orcid.org/0000-0001-5022-5716","observed_orcids":["https://orcid.org/0000-0001-5022-5716"]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Israt Nisa","raw_affiliation_strings":["AWS AI, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101452217","display_name":"Minjie Wang","orcid":"https://orcid.org/0000-0001-8830-6079","observed_orcids":["https://orcid.org/0000-0001-8830-6079"]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minjie Wang","raw_affiliation_strings":["AWS AI, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI, Shanghai, China","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060763203","display_name":"Da Zheng","orcid":"https://orcid.org/0000-0001-8115-5415","observed_orcids":["https://orcid.org/0000-0001-8115-5415"]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Da Zheng","raw_affiliation_strings":["AWS AI, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086820941","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0002-5821-7267","observed_orcids":["https://orcid.org/0000-0002-5821-7267"]},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["George Washington University, Washington, DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026046737","display_name":"\u00dcmit V. \u00c7ataly\u00fcrek","orcid":"https://orcid.org/0000-0002-5625-3758","observed_orcids":["https://orcid.org/0000-0002-5625-3758"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"\u00dcmit \u00c7ataly\u00fcrek","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082384108","display_name":"George Karypis","orcid":"https://orcid.org/0000-0003-2753-1437","observed_orcids":["https://orcid.org/0000-0003-2753-1437"]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Karypis","raw_affiliation_strings":["AWS AI, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2209,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42295735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":"32","issue":null,"first_page":"199","last_page":"206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.4772999882698059,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.4772999882698059,"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"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.46950000524520874,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.03779999911785126,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/heterogeneous-graph-neural-networks","display_name":"heterogeneous graph neural networks","score":0.9269999861717224},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.48500001430511475},{"id":"https://openalex.org/keywords/mini-batch-training","display_name":"mini-batch training","score":0.7820000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670356035232544},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5078063607215881},{"id":"https://openalex.org/C158207573","wikidata":"https://www.wikidata.org/wiki/Q5747224","display_name":"Heterogeneous network","level":4,"score":0.5060448050498962},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4994547367095947},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.47108662128448486},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4634445011615753},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.42736196517944336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38638511300086975},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3535849153995514},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30401867628097534},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3017127513885498},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.14030158519744873},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13704892992973328},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw59300.2023.00042","doi":"https://doi.org/10.1109/ipdpsw59300.2023.00042","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ipdpsw59300.2023.00042","pdf_url":null,"source":{"id":"https://openalex.org/S4393918253","display_name":"IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum","issn_l":"2164-7062","issn":["2164-7062"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2127795553","https://openalex.org/W2186615578","https://openalex.org/W2402144811","https://openalex.org/W2604314403","https://openalex.org/W2808128431","https://openalex.org/W2911286998","https://openalex.org/W2912064332","https://openalex.org/W2914631005","https://openalex.org/W2918342466","https://openalex.org/W2965857891","https://openalex.org/W2970971581","https://openalex.org/W2971933740","https://openalex.org/W3012871709","https://openalex.org/W3168547639","https://openalex.org/W3175498521","https://openalex.org/W4285045111","https://openalex.org/W4327911434","https://openalex.org/W4395116186","https://openalex.org/W6849343812"],"related_works":["https://openalex.org/W4321636644","https://openalex.org/W4386148447","https://openalex.org/W4399282122","https://openalex.org/W7162466782","https://openalex.org/W4409653046","https://openalex.org/W7213271457","https://openalex.org/W4395116186","https://openalex.org/W4407578032","https://openalex.org/W4401726150","https://openalex.org/W4384705419"],"abstract_inverted_index":{"GNN":[0,29,45,91],"models":[1,52,92],"on":[2],"heterogeneous":[3,44,90],"graphs":[4],"have":[5],"achieved":[6],"state-of-the-art":[7],"(SOTA)":[8],"performance":[9],"in":[10,24,86],"various":[11],"graph":[12],"tasks":[13],"such":[14,31],"as":[15,32],"link":[16],"prediction":[17],"and":[18,34,40,56,72,95,111],"node":[19],"classification.":[20],"Despite":[21],"their":[22],"success":[23],"providing":[25],"SOTA":[26],"results,":[27],"popular":[28,89],"libraries,":[30],"PyG":[33],"DGL,":[35],"fail":[36],"to":[37,74,109,115],"provide":[38],"fast":[39],"efficient":[41],"solutions":[42],"for":[43],"models.":[46],"One":[47],"common":[48],"key":[49],"bottlenecks":[50],"of":[51,82,105],"like":[53],"RGAT,":[54],"RGCN,":[55],"HGT":[57],"is":[58],"relation-specific":[59],"linear":[60],"projection.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"propose":[66],"two":[67,88],"high-performing":[68],"tensor":[69],"operators:":[70],"gather-mm":[71],"segment-mm":[73],"address":[75],"the":[76,80,83,101],"issue.":[77],"We":[78],"demonstrate":[79],"effectiveness":[81],"proposed":[84,98],"operators":[85],"training":[87,103],"\u2013":[93],"RGCN":[94,106],"HGT.":[96],"Our":[97],"approaches":[99],"outperform":[100],"full-batch":[102],"time":[104],"by":[107,113],"up":[108,114],"3\u00d7":[110],"mini-batch":[112],"2\u00d7.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-08-05T00:00:00"}