{"id":"https://openalex.org/W4401863494","doi":"https://doi.org/10.1145/3637528.3671699","title":"AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation","display_name":"AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863494","doi":"https://doi.org/10.1145/3637528.3671699"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671699","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery 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/A5057511843","display_name":"Weigang Lu","orcid":"https://orcid.org/0000-0003-4855-7070"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weigang Lu","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065194313","display_name":"Ziyu Guan","orcid":"https://orcid.org/0000-0003-2413-4698"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Guan","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066877556","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0002-0622-9258"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["Xidian University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007002324","display_name":"Yaming Yang","orcid":"https://orcid.org/0000-0002-8186-0648"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaming Yang","raw_affiliation_strings":["Xidian University, Xi'an, Shannxi, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, Shannxi, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057511843"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":3.0735,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92474349,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2060","last_page":"2071"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9943000078201294,"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/T10028","display_name":"Topic Modeling","score":0.9943000078201294,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9925000071525574,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.989799976348877,"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/distillation","display_name":"Distillation","score":0.7577327489852905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6362533569335938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4041215777397156},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3327614963054657},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.2383905053138733},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.14580336213111877}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7577327489852905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6362533569335938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4041215777397156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3327614963054657},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.2383905053138733},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.14580336213111877}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671699","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery 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/W1534477342","https://openalex.org/W2075157159","https://openalex.org/W2162630660","https://openalex.org/W2168190036","https://openalex.org/W2560674852","https://openalex.org/W2914721378","https://openalex.org/W2987861506","https://openalex.org/W3015858876","https://openalex.org/W3030204405","https://openalex.org/W3034795332","https://openalex.org/W3080083111","https://openalex.org/W3121087702","https://openalex.org/W3152626252","https://openalex.org/W3212385273","https://openalex.org/W4210841708","https://openalex.org/W4385819812","https://openalex.org/W4393156544","https://openalex.org/W4394744523","https://openalex.org/W6603850445"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4,166],"revolutionized":[5],"graph-based":[6],"machine":[7],"learning,":[8],"but":[9],"their":[10,80],"heavy":[11],"computational":[12],"demands":[13],"pose":[14],"challenges":[15,68],"for":[16,127,157],"latency-sensitive":[17,162],"edge":[18],"devices":[19],"in":[20,69,82],"practical":[21],"industrial":[22],"applications.":[23,84,164],"In":[24],"response,":[25],"a":[26,46,123,158],"new":[27],"wave":[28],"of":[29,102,110,116,161],"methods,":[30,153],"collectively":[31],"known":[32],"as":[33],"GNN-to-MLP":[34,94],"Knowledge":[35,95],"Distillation,":[36],"has":[37],"emerged.":[38],"They":[39],"aim":[40],"to":[41,45,61,170],"transfer":[42],"GNN-learned":[43],"knowledge":[44],"more":[47],"efficient":[48],"MLP":[49,104],"student,":[50],"which":[51],"offers":[52],"faster,":[53],"resource-efficient":[54],"inference":[55],"while":[56],"maintaining":[57],"competitive":[58],"performance":[59],"compared":[60],"GNNs.":[62],"However,":[63],"these":[64,87],"methods":[65],"face":[66],"significant":[67],"situations":[70],"with":[71,133,144],"insufficient":[72,117],"training":[73,118],"data":[74,132],"and":[75],"incomplete":[76,136],"test":[77,131],"data,":[78],"limiting":[79],"applicability":[81],"real-world":[83,163],"To":[85],"address":[86],"challenges,":[88],"we":[89],"propose":[90],"AdaGMLP,":[91],"an":[92,100],"AdaBoosting":[93],"Distillation":[96],"framework.":[97],"It":[98],"leverages":[99],"ensemble":[101],"diverse":[103],"students":[105],"trained":[106],"on":[107,130,140],"different":[108,145],"subsets":[109],"labeled":[111],"nodes,":[112],"addressing":[113],"the":[114,171],"issue":[115],"data.":[119],"Additionally,":[120],"it":[121,155],"incorporates":[122],"Node":[124],"Alignment":[125],"technique":[126],"robust":[128],"predictions":[129],"missing":[134],"or":[135],"features.":[137],"Our":[138],"experiments":[139],"seven":[141],"benchmark":[142],"datasets":[143],"settings":[146],"demonstrate":[147],"that":[148],"AdaGMLP":[149],"outperforms":[150],"existing":[151],"G2M":[152],"making":[154],"suitable":[156],"wide":[159],"range":[160],"We":[165],"submitted":[167],"our":[168],"code":[169],"GitHub":[172],"repository":[173],"(https://github.com/WeigangLu/AdaGMLP-KDD24).":[174]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}