{"id":"https://openalex.org/W3215602976","doi":"https://doi.org/10.1145/3616855.3635802","title":"Source Free Graph Unsupervised Domain Adaptation","display_name":"Source Free Graph Unsupervised Domain Adaptation","publication_year":2024,"publication_date":"2024-03-04","ids":{"openalex":"https://openalex.org/W3215602976","doi":"https://doi.org/10.1145/3616855.3635802","mag":"3215602976"},"language":"en","primary_location":{"id":"doi:10.1145/3616855.3635802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616855.3635802","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635802","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635802","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065066091","display_name":"Haitao Mao","orcid":"https://orcid.org/0009-0000-8510-3102"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haitao Mao","raw_affiliation_strings":["Michigan State University, East Lansing, USA"],"raw_orcid":"https://orcid.org/0009-0000-8510-3102","affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008387608","display_name":"Lun Du","orcid":"https://orcid.org/0000-0002-7625-0650"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lun Du","raw_affiliation_strings":["Microsoft, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7625-0650","affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004130985","display_name":"Yujia Zheng","orcid":"https://orcid.org/0009-0003-5225-6366"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yujia Zheng","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0009-0003-5225-6366","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086820941","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0002-5821-7267"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Microsoft, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5821-7267","affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665554","display_name":"Zelin Li","orcid":"https://orcid.org/0009-0000-6976-9510"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zelin Li","raw_affiliation_strings":["Microsoft, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-6976-9510","affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100711699","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0001-5041-0532"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["Microsoft, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5041-0532","affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006300825","display_name":"Shi Han","orcid":"https://orcid.org/0000-0002-0360-6089"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Han","raw_affiliation_strings":["Microsoft, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0360-6089","affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331488","display_name":"Dongmei Zhang","orcid":"https://orcid.org/0000-0002-9230-2799"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Zhang","raw_affiliation_strings":["Microsoft, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9230-2799","affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5065066091"],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":2.6491,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90439546,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"520","last_page":"528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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/T12676","display_name":"Machine Learning and ELM","score":0.9890999794006348,"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":0.7829724550247192},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.598652720451355},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5945935249328613},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5684633255004883},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5183435678482056},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4734891355037689},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.46724891662597656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4090527296066284},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38081222772598267},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3560987114906311},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.10660251975059509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829724550247192},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.598652720451355},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5945935249328613},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5684633255004883},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5183435678482056},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4734891355037689},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46724891662597656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4090527296066284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38081222772598267},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3560987114906311},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.10660251975059509},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3616855.3635802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616855.3635802","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635802","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2112.00955","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.00955","pdf_url":"https://arxiv.org/pdf/2112.00955","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3616855.3635802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616855.3635802","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635802","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3215602976.pdf","grobid_xml":"https://content.openalex.org/works/W3215602976.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1565327149","https://openalex.org/W1882958252","https://openalex.org/W1998894210","https://openalex.org/W2022322548","https://openalex.org/W2099438806","https://openalex.org/W2102848467","https://openalex.org/W2111362445","https://openalex.org/W2154851992","https://openalex.org/W2164943005","https://openalex.org/W2187089797","https://openalex.org/W2593414223","https://openalex.org/W2594718649","https://openalex.org/W2607500032","https://openalex.org/W2744999500","https://openalex.org/W2792234394","https://openalex.org/W2911752833","https://openalex.org/W2913243576","https://openalex.org/W2962756421","https://openalex.org/W2962767366","https://openalex.org/W2963826681","https://openalex.org/W2963858333","https://openalex.org/W2964015378","https://openalex.org/W2964121744","https://openalex.org/W2964321699","https://openalex.org/W2965115497","https://openalex.org/W2997964288","https://openalex.org/W3005552578","https://openalex.org/W3012644407","https://openalex.org/W3012663529","https://openalex.org/W3033039844","https://openalex.org/W3033623365","https://openalex.org/W3034218934","https://openalex.org/W3034526587","https://openalex.org/W3035237680","https://openalex.org/W3036446966","https://openalex.org/W3037208489","https://openalex.org/W3093803318","https://openalex.org/W3101444938","https://openalex.org/W3104097132","https://openalex.org/W3105705953","https://openalex.org/W3112479687","https://openalex.org/W3173716304","https://openalex.org/W3175818609","https://openalex.org/W3206947356","https://openalex.org/W3207379368","https://openalex.org/W3212781537","https://openalex.org/W4285723986","https://openalex.org/W4287755125","https://openalex.org/W4288337233","https://openalex.org/W4290875057","https://openalex.org/W4294558607","https://openalex.org/W4297571622","https://openalex.org/W4304194366","https://openalex.org/W4312365002","https://openalex.org/W4362598285","https://openalex.org/W4379473885","https://openalex.org/W4387323920","https://openalex.org/W6707620307","https://openalex.org/W6755573351"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4283211831","https://openalex.org/W4297577100","https://openalex.org/W2798287483","https://openalex.org/W2963261224"],"abstract_inverted_index":{"Graph":[0,25,125],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4],"achieved":[5],"great":[6],"success":[7],"on":[8,56,69,92,204,223],"a":[9,45,118,158,179],"variety":[10],"of":[11,33,112,193,201,212],"tasks":[12,226],"with":[13],"graph-structural":[14],"data,":[15],"among":[16],"which":[17],"node":[18,39],"classification":[19],"is":[20,109,142],"an":[21],"essential":[22],"one.":[23],"Unsupervised":[24,124],"Domain":[26,126],"Adaptation":[27,127],"(UGDA)":[28],"shows":[29],"its":[30,155],"practical":[31,175],"value":[32],"reducing":[34],"the":[35,53,70,74,81,85,94,98,106,132,139,143,151,169,190,194,199,205,210,213,231],"labeling":[36],"cost":[37],"for":[38,184],"classification.":[40],"It":[41],"leverages":[42],"knowledge":[43],"from":[44,80,138],"labeled":[46,71],"graph":[47,59,72,96,108,153],"(i.e.,":[48,60],"source":[49,75,82,95,107,140,145,152,195],"domain)":[50],"to":[51,150,187],"tackle":[52],"same":[54],"task":[55],"another":[57],"unlabeled":[58],"target":[61,99,206],"domain).":[62],"Most":[63],"existing":[64,160],"UGDA":[65,161],"methods":[66,162],"heavily":[67],"rely":[68],"in":[73,102,173,230],"domain.":[76],"They":[77],"utilize":[78],"labels":[79],"domain":[83,141,185],"as":[84],"supervision":[86],"signal":[87],"and":[88,97,154,218,234],"are":[89,163],"jointly":[90],"trained":[91],"both":[93,216],"graph.":[100,207],"However,":[101],"some":[103],"real-world":[104],"scenarios,":[105],"inaccessible":[110],"because":[111],"privacy":[113],"issues.":[114],"Therefore,":[115],"we":[116,135,177],"propose":[117,178],"novel":[119],"scenario":[120],"named":[121],"Source":[122],"Free":[123],"(SFUGDA).":[128],"In":[129],"this":[130,174],"scenario,":[131,176],"only":[133],"information":[134],"can":[136],"leverage":[137],"well-trained":[144],"model,":[146],"without":[147],"any":[148],"exposure":[149],"labels.":[156],"As":[157],"result,":[159],"not":[164],"feasible":[165],"anymore.":[166],"To":[167],"address":[168],"non-trivial":[170],"adaptation":[171,186],"challenges":[172],"model-agnostic":[180],"algorithm":[181,215],"called":[182],"SOGA":[183],"fully":[188],"exploit":[189],"discriminative":[191],"ability":[192],"model":[196],"while":[197],"preserving":[198],"consistency":[200],"structural":[202],"proximity":[203],"We":[208],"prove":[209],"effectiveness":[211],"proposed":[214],"theoretically":[217],"empirically.":[219],"The":[220],"experimental":[221],"results":[222],"four":[224],"cross-domain":[225],"show":[227],"consistent":[228],"improvements":[229],"Macro-F1":[232],"score":[233],"Macro-AUC.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-12-06T00:00:00"}