{"id":"https://openalex.org/W4321480064","doi":"https://doi.org/10.1145/3539597.3570480","title":"Learning to Distill Graph Neural Networks","display_name":"Learning to Distill Graph Neural Networks","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4321480064","doi":"https://doi.org/10.1145/3539597.3570480"},"language":"en","primary_location":{"id":"doi:10.1145/3539597.3570480","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","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/A5060417049","display_name":"Cheng Yang","orcid":"https://orcid.org/0000-0001-7821-0030"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cheng Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051713264","display_name":"Yuxin Guo","orcid":"https://orcid.org/0000-0003-1913-014X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Guo","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072316323","display_name":"Yao Xu","orcid":"https://orcid.org/0000-0002-4748-8133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Xu","raw_affiliation_strings":["Researcher, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Researcher, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705849","display_name":"Chuan Shi","orcid":"https://orcid.org/0000-0002-3734-0266"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Shi","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101834031","display_name":"Jiawei Liu","orcid":"https://orcid.org/0000-0003-2437-0455"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089434534","display_name":"Chunchen Wang","orcid":"https://orcid.org/0000-0002-5778-9490"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunchen Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353721","display_name":"Xin Li","orcid":"https://orcid.org/0000-0001-6888-7064"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Researcher, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Researcher, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020113235","display_name":"Ning Guo","orcid":"https://orcid.org/0000-0003-2292-432X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Guo","raw_affiliation_strings":["Researcher, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Researcher, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088492734","display_name":"Hongzhi Yin","orcid":"https://orcid.org/0000-0003-1395-261X"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hongzhi Yin","raw_affiliation_strings":["The University of Queensland, Brisbane, QLD, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5060417049"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":1.3917,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84268837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"131"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9886000156402588,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9861999750137329,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8030439615249634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7761956453323364},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7444840669631958},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6429595947265625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.607616126537323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5139936804771423},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49901461601257324},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4963398575782776},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48970797657966614},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4858109951019287},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.23368093371391296},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07422670722007751}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8030439615249634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7761956453323364},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7444840669631958},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6429595947265625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.607616126537323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5139936804771423},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49901461601257324},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4963398575782776},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48970797657966614},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4858109951019287},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.23368093371391296},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07422670722007751},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539597.3570480","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2579549467","https://openalex.org/W2600702321","https://openalex.org/W2951626691","https://openalex.org/W2962779575","https://openalex.org/W3030204405","https://openalex.org/W3034795332","https://openalex.org/W3080083111","https://openalex.org/W3088663932","https://openalex.org/W3108124733","https://openalex.org/W3123223876","https://openalex.org/W3148088798","https://openalex.org/W3150739942","https://openalex.org/W3152626252","https://openalex.org/W3167936733","https://openalex.org/W3174048174","https://openalex.org/W3176189116","https://openalex.org/W3192084854","https://openalex.org/W4212842481","https://openalex.org/W4285216485"],"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],"Neural":[1],"Networks":[2],"(GNNs)":[3],"can":[4,99,207],"effectively":[5],"capture":[6],"both":[7],"the":[8,43,70,114,228,238],"topology":[9],"and":[10,16,79,121,167,169,180,215],"attribute":[11],"information":[12],"of":[13,45,72,131,151,163,189,240],"a":[14,93,133,161,172,186],"graph,":[15],"have":[17],"been":[18],"extensively":[19],"studied":[20],"in":[21],"many":[22],"domains.":[23],"Recently,":[24],"there":[25],"is":[26],"an":[27],"emerging":[28],"trend":[29],"that":[30,98,203],"equips":[31],"GNNs":[32,54],"with":[33,221],"knowledge":[34,49,95],"distillation":[35,50,58,78,96,123,146],"for":[36,126,177],"better":[37,149],"efficiency":[38],"or":[39],"effectiveness.":[40],"However,":[41],"to":[42,83,91,107,119,192],"best":[44],"our":[46,190,204],"knowledge,":[47],"existing":[48],"methods":[51],"applied":[52,101,209],"on":[53,102,198,210,225],"all":[55],"employed":[56],"predefined":[57],"processes,":[59],"which":[60],"are":[61],"controlled":[62],"by":[63,160],"several":[64],"hyper-parameters":[65],"without":[66],"any":[67,103],"supervision":[68],"from":[69],"performance":[71,150],"distilled":[73,152],"models.":[74,153],"Such":[75],"isolation":[76,115],"between":[77],"evaluation":[80],"would":[81],"lead":[82],"suboptimal":[84],"results.":[85],"In":[86],"this":[87],"work,":[88],"we":[89,117,142],"aim":[90],"propose":[92,118],"general":[94],"framework":[97,206],"be":[100,208],"pretrained":[104],"GNN":[105,213],"models":[106,214],"further":[108],"improve":[109,217],"their":[110,218],"performance.":[111],"To":[112],"address":[113],"problem,":[116],"parameterize":[120,156],"learn":[122,144],"processes":[124],"suitable":[125],"distilling":[127,179],"GNNs.":[128],"Specifically,":[129],"instead":[130],"introducing":[132],"unified":[134],"temperature":[135,159,181],"hyper-parameter":[136],"as":[137],"most":[138],"previous":[139],"work":[140],"did,":[141],"will":[143],"node-specific":[145],"temperatures":[147],"towards":[148],"We":[154,183],"first":[155],"each":[157],"node's":[158],"function":[162],"its":[164],"neighborhood's":[165],"encodings":[166],"predictions,":[168],"then":[170],"design":[171],"novel":[173],"iterative":[174],"learning":[175],"process":[176],"model":[178,194],"learning.":[182],"also":[184],"introduce":[185],"scalable":[187,229],"variant":[188,230],"method":[191],"accelerate":[193],"training.":[195],"Experimental":[196],"results":[197],"five":[199,211],"benchmark":[200],"datasets":[201],"show":[202],"proposed":[205],"popular":[212],"consistently":[216],"prediction":[219,242],"accuracies":[220],"3.12%":[222],"relative":[223],"enhancement":[224],"average.":[226],"Besides,":[227],"enables":[231],"8":[232],"times":[233],"faster":[234],"training":[235],"speed":[236],"at":[237],"cost":[239],"1%":[241],"accuracy.":[243]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}