{"id":"https://openalex.org/W3080510905","doi":"https://doi.org/10.1145/3394486.3403088","title":"Policy-GNN: Aggregation Optimization for Graph Neural Networks","display_name":"Policy-GNN: Aggregation Optimization for Graph Neural Networks","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3080510905","doi":"https://doi.org/10.1145/3394486.3403088","mag":"3080510905"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403088","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403088","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403088","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403088","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089183436","display_name":"Kwei-Herng Lai","orcid":"https://orcid.org/0000-0001-8933-7117"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwei-Herng Lai","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058071176","display_name":"Daochen Zha","orcid":"https://orcid.org/0000-0002-6677-7504"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daochen Zha","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071607114","display_name":"Kaixiong Zhou","orcid":"https://orcid.org/0000-0001-5226-8736"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaixiong Zhou","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068477431","display_name":"Xia Hu","orcid":"https://orcid.org/0000-0003-2234-3226"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xia Hu","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":87,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"461","last_page":"471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998999834060669,"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":0.9998999834060669,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.98580002784729,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9746000170707703,"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/computer-science","display_name":"Computer science","score":0.8578977584838867},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6982896327972412},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6514698266983032},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6033825874328613},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.46795403957366943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4467924237251282},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41599640250205994},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41592225432395935},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3705785870552063},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32165515422821045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8578977584838867},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6982896327972412},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6514698266983032},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6033825874328613},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.46795403957366943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4467924237251282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41599640250205994},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41592225432395935},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3705785870552063},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32165515422821045},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394486.3403088","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403088","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403088","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3394486.3403088","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403088","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403088","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G1508080283","display_name":null,"funder_award_id":"IIS-1718840,IIS-1750074","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2220043244","display_name":null,"funder_award_id":"IIS-1718840","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5913764691","display_name":null,"funder_award_id":"IIS-1750074","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6604742037","display_name":"CAREER: Human-Centric Big Network Embedding","funder_award_id":"1750074","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8766092123","display_name":"III: Small: Collaborative Research: A General Feature Learning Framework for Dynamic Attributed Networks","funder_award_id":"1718840","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3080510905.pdf","grobid_xml":"https://content.openalex.org/works/W3080510905.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2107474859","https://openalex.org/W2112796928","https://openalex.org/W2116341502","https://openalex.org/W2142498761","https://openalex.org/W2145339207","https://openalex.org/W2154851992","https://openalex.org/W2519887557","https://openalex.org/W2593744649","https://openalex.org/W2605350416","https://openalex.org/W2624431344","https://openalex.org/W2755092149","https://openalex.org/W2786915849","https://openalex.org/W2803767077","https://openalex.org/W2890703109","https://openalex.org/W2918342466","https://openalex.org/W2950133940","https://openalex.org/W2950880273","https://openalex.org/W2962756421","https://openalex.org/W2963521729","https://openalex.org/W2963858333","https://openalex.org/W2964321699","https://openalex.org/W2965870268","https://openalex.org/W2968406604","https://openalex.org/W3011120880","https://openalex.org/W3023012876","https://openalex.org/W3104097132","https://openalex.org/W3105136071","https://openalex.org/W3160202947"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Graph":[0],"data":[1],"are":[2],"pervasive":[3],"in":[4,61,214],"many":[5],"real-world":[6,200],"applications.":[7],"Recently,":[8],"increasing":[9],"attention":[10],"has":[11],"been":[12],"paid":[13],"on":[14,198],"graph":[15,25],"neural":[16],"networks":[17],"(GNNs),":[18],"which":[19],"aim":[20],"to":[21,55,66,76,87,107,115,157,191],"model":[22],"the":[23,29,34,44,58,78,117,128,139,160,177,180,193,208,212],"local":[24],"structures":[26],"and":[27,99,142,187],"capture":[28,57],"hierarchical":[30],"patterns":[31],"by":[32,43,175],"aggregating":[33],"information":[35],"from":[36,179],"neighbors":[37],"with":[38,171],"stackable":[39],"network":[40,124],"modules.":[41],"Motivated":[42],"observation":[45],"that":[46,137,204],"different":[47,51,74,121],"nodes":[48,75,119],"often":[49],"require":[50],"iterations":[52,70],"of":[53,71,80,123,145,162],"aggregation":[54,72,91,215],"fully":[56],"structural":[59],"information,":[60],"this":[62],"paper,":[63],"we":[64,113,131],"propose":[65,132],"explicitly":[67],"sample":[68],"diverse":[69],"for":[73,93,164,217],"boost":[77,192],"performance":[79],"GNNs.":[81,218],"It":[82],"is":[83,104,169],"a":[84,134,148,155,188],"challenging":[85],"task":[86],"develop":[88],"an":[89,109],"effective":[90],"strategy":[92],"each":[94,165],"node,":[95],"given":[96],"complex":[97],"graphs":[98],"sparse":[100],"features.":[101],"Moreover,":[102],"it":[103],"not":[105],"straightforward":[106],"derive":[108],"efficient":[110],"algorithm":[111],"since":[112],"need":[114],"feed":[116],"sampled":[118],"into":[120,147],"number":[122,161],"layers.":[125],"To":[126],"address":[127],"above":[129],"challenges,":[130],"Policy-GNN,":[133],"meta-policy":[135,156,168],"framework":[136],"models":[138],"sampling":[140],"procedure":[141],"message":[143],"passing":[144],"GNNs":[146],"combined":[149],"learning":[150],"process.":[151],"Specifically,":[152],"Policy-GNN":[153,205],"uses":[154],"adaptively":[158],"determine":[159],"aggregations":[163],"node.":[166],"The":[167],"trained":[170],"deep":[172],"reinforcement":[173],"learning~(RL)":[174],"exploiting":[176],"feedback":[178],"model.":[181],"We":[182],"further":[183],"introduce":[184],"parameter":[185],"sharing":[186],"buffer":[189],"mechanism":[190],"training":[194],"efficiency.":[195],"Experimental":[196],"results":[197],"three":[199],"benchmark":[201],"datasets":[202],"suggest":[203],"significantly":[206],"outperforms":[207],"state-of-the-art":[209],"alternatives,":[210],"showing":[211],"promise":[213],"optimization":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}