{"id":"https://openalex.org/W3216171780","doi":"https://doi.org/10.1145/3489517.3530416","title":"Efficient ensembles of graph neural networks","display_name":"Efficient ensembles of graph neural networks","publication_year":2022,"publication_date":"2022-07-10","ids":{"openalex":"https://openalex.org/W3216171780","doi":"https://doi.org/10.1145/3489517.3530416","mag":"3216171780"},"language":"en","primary_location":{"id":"doi:10.1145/3489517.3530416","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3489517.3530416","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3489517.3530416","source":{"id":"https://openalex.org/S4363608816","display_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3489517.3530416","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063948719","display_name":"Amrit Nagarajan","orcid":"https://orcid.org/0000-0002-2847-4721"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amrit Nagarajan","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044634700","display_name":"Jacob R. Stevens","orcid":"https://orcid.org/0000-0002-7626-2846"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob R. Stevens","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065766721","display_name":"Anand Raghunathan","orcid":"https://orcid.org/0000-0002-4624-564X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Raghunathan","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063948719"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":1.5962,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80452453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"187","last_page":"192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8267576694488525},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6681268215179443},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.5650158524513245},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5032321810722351},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5024824142456055},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4938143193721771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47679686546325684},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4726128876209259},{"id":"https://openalex.org/keywords/mean-squared-prediction-error","display_name":"Mean squared prediction error","score":0.452802449464798},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4444044232368469},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35552117228507996},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.29383528232574463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267576694488525},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6681268215179443},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.5650158524513245},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5032321810722351},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5024824142456055},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4938143193721771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47679686546325684},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4726128876209259},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.452802449464798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4444044232368469},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35552117228507996},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29383528232574463},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3489517.3530416","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3489517.3530416","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3489517.3530416","source":{"id":"https://openalex.org/S4363608816","display_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3489517.3530416","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3489517.3530416","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3489517.3530416","source":{"id":"https://openalex.org/S4363608816","display_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 59th ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3216171780.pdf","grobid_xml":"https://content.openalex.org/works/W3216171780.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W1982970530","https://openalex.org/W1998917233","https://openalex.org/W3201150168"],"related_works":["https://openalex.org/W4285741730","https://openalex.org/W4318677156","https://openalex.org/W4376643315","https://openalex.org/W4281560664","https://openalex.org/W4292969247","https://openalex.org/W3151529617","https://openalex.org/W3136979370","https://openalex.org/W4293069612","https://openalex.org/W4220785415","https://openalex.org/W3214927170"],"abstract_inverted_index":{"Ensembles":[0,26],"improve":[1,78],"the":[2,68,72,79],"accuracy":[3,58],"and":[4,16,50,59,90,109],"robustness":[5],"of":[6,67,81],"Graph":[7],"Neural":[8],"Networks":[9],"(GNNs),":[10],"but":[11],"suffer":[12],"from":[13],"high":[14],"latency":[15],"storage":[17],"requirements.":[18],"To":[19,77],"address":[20],"this":[21],"challenge,":[22],"we":[23,83],"propose":[24,84],"GNN":[25,120],"through":[27],"Error":[28],"Node":[29],"Isolation":[30],"(GEENI).":[31],"The":[32],"key":[33],"concept":[34],"in":[35,71],"GEENI":[36,62,99],"is":[37],"to":[38,44,56,104,111,116],"identify":[39],"nodes":[40],"that":[41,98],"are":[42,101],"likely":[43],"be":[45],"incorrectly":[46],"classified":[47],"(error":[48],"nodes)":[49],"suppress":[51],"their":[52],"outgoing":[53],"messages,":[54],"leading":[55],"simultaneous":[57],"efficiency":[60],"improvements.":[61],"also":[63],"enables":[64],"aggressive":[65],"approximations":[66],"constituent":[69],"models":[70,100],"ensemble":[73,88],"while":[74],"maintaining":[75],"accuracy.":[76],"efficacy":[80],"GEENI,":[82],"techniques":[85],"for":[86],"diverse":[87],"creation":[89],"accurate":[91,108],"error":[92],"node":[93],"identification.":[94],"Our":[95],"experiments":[96],"establish":[97],"simultaneously":[102],"up":[103,110],"4.6%":[105],"(3.8%)":[106],"more":[107],"2.8X":[112],"(5.7X)":[113],"faster":[114],"compared":[115],"non-ensemble":[117],"(conventional":[118],"ensemble)":[119],"models.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}