{"id":"https://openalex.org/W4321479940","doi":"https://doi.org/10.1145/3539597.3570404","title":"S2GAE: Self-Supervised Graph Autoencoders are Generalizable Learners with Graph Masking","display_name":"S2GAE: Self-Supervised Graph Autoencoders are Generalizable Learners with Graph Masking","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4321479940","doi":"https://doi.org/10.1145/3539597.3570404"},"language":"en","primary_location":{"id":"doi:10.1145/3539597.3570404","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539597.3570404","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539597.3570404","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":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3539597.3570404","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043697901","display_name":"Qiaoyu Tan","orcid":"https://orcid.org/0000-0001-8999-968X"},"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":true,"raw_author_name":"Qiaoyu Tan","raw_affiliation_strings":["Texas A&M University, College station, TX, USA"],"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/A5007489034","display_name":"Ninghao Liu","orcid":"https://orcid.org/0000-0002-9170-2424"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ninghao Liu","raw_affiliation_strings":["University of Georgia, Athens, GA, USA"],"affiliations":[{"raw_affiliation_string":"University of Georgia, Athens, GA, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055037545","display_name":"Xiao Huang","orcid":"https://orcid.org/0000-0002-3867-900X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiao Huang","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027525032","display_name":"Soo-Hyun Choi","orcid":"https://orcid.org/0000-0001-5768-9978"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soo-Hyun Choi","raw_affiliation_strings":["Samsung Electronics, Mountain view, CA, USA"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics, Mountain view, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361140","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-3365-8904"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Samsung Electronics America, Mountain view, CA, USA"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics America, Mountain view, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004491098","display_name":"Rui Chen","orcid":"https://orcid.org/0000-0002-8161-7365"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Chen","raw_affiliation_strings":["Samsung Electronics America, Mountain view, CA, USA"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics America, Mountain view, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"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/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xia Hu","raw_affiliation_strings":["Rice University, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5043697901"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":17.6071,"has_fulltext":true,"cited_by_count":102,"citation_normalized_percentile":{"value":0.99483643,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"787","last_page":"795"},"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10269","display_name":"Epigenetics and DNA Methylation","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8111518621444702},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.70977783203125},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6404834389686584},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5759851932525635},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.500443696975708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4971006214618683},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4879014194011688},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4587152302265167},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43190449476242065},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41345635056495667},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4103521704673767},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33572039008140564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8111518621444702},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.70977783203125},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6404834389686584},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5759851932525635},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.500443696975708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4971006214618683},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4879014194011688},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4587152302265167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43190449476242065},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41345635056495667},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4103521704673767},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33572039008140564},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539597.3570404","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539597.3570404","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539597.3570404","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":{"id":"doi:10.1145/3539597.3570404","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539597.3570404","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539597.3570404","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"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2693525634","display_name":null,"funder_award_id":"1849085","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5144224888","display_name":null,"funder_award_id":"IIS-184908","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5560190241","display_name":null,"funder_award_id":"IIS-1849085","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/G7378744750","display_name":null,"funder_award_id":"2006844","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4321479940.pdf","grobid_xml":"https://content.openalex.org/works/W4321479940.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2008857988","https://openalex.org/W2153635508","https://openalex.org/W2153959628","https://openalex.org/W2154851992","https://openalex.org/W2623187518","https://openalex.org/W2624431344","https://openalex.org/W2908461307","https://openalex.org/W2925587834","https://openalex.org/W2962756421","https://openalex.org/W2981450816","https://openalex.org/W3005680577","https://openalex.org/W3012833893","https://openalex.org/W3034693603","https://openalex.org/W3037208489","https://openalex.org/W3040213512","https://openalex.org/W3080456792","https://openalex.org/W3081203761","https://openalex.org/W3095602948","https://openalex.org/W3095746859","https://openalex.org/W3103254545","https://openalex.org/W3104097132","https://openalex.org/W3104425534","https://openalex.org/W3129197243","https://openalex.org/W3154503084","https://openalex.org/W3160875407","https://openalex.org/W3168406300","https://openalex.org/W3173151551","https://openalex.org/W3204453541","https://openalex.org/W3209752990","https://openalex.org/W4287121295","https://openalex.org/W4288278932","https://openalex.org/W4312206464","https://openalex.org/W6633728996","https://openalex.org/W6681029592","https://openalex.org/W6739901393","https://openalex.org/W6784694379","https://openalex.org/W6910499371","https://openalex.org/W7067525586"],"related_works":["https://openalex.org/W4309201921","https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4220682630","https://openalex.org/W4389832810","https://openalex.org/W3163146846"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,177],"(SSL)":[2],"has":[3,30],"been":[4,31],"demonstrated":[5],"to":[6,16,34,91,149],"be":[7,14,171],"effective":[8,156],"in":[9],"pre-training":[10],"models":[11],"that":[12,45,86,168],"can":[13,88],"generalized":[15],"various":[17],"downstream":[18],"tasks.":[19,203],"Graph":[20,119],"Autoencoder":[21],"(GAE),":[22],"an":[23,155,160,174],"increasingly":[24],"popular":[25],"SSL":[26],"approach":[27],"on":[28,53,60,70,191,229],"graphs,":[29],"widely":[32],"explored":[33],"learn":[35,148],"node":[36,199],"representations":[37],"without":[38],"ground-truth":[39],"labels.":[40],"However,":[41],"recent":[42],"studies":[43],"show":[44,85],"existing":[46],"GAE":[47,87,223],"methods":[48],"could":[49,170],"only":[50],"perform":[51],"well":[52,90],"link":[54,93,196],"prediction":[55,94,197],"tasks,":[56,102],"while":[57],"their":[58],"performance":[59],"classification":[61,96,202],"tasks":[62],"is":[63,116,233],"rather":[64],"limited.":[65],"This":[66,217],"limitation":[67],"casts":[68],"doubt":[69],"the":[71,81,110,123,136,207,220],"generalizability":[72],"and":[73,95,100,147,159,198,214],"adoption":[74],"of":[75,125,134,145,209,222],"GAE.":[76],"In":[77],"this":[78],"paper,":[79],"for":[80],"first":[82],"time,":[83],"we":[84,140,165,187],"generalize":[89],"both":[92],"scenarios,":[97],"including":[98],"node-level":[99],"graph-level":[101],"by":[103],"redesigning":[104],"its":[105],"critical":[106],"building":[107],"blocks":[108],"from":[109],"graph":[111,201],"masking":[112,157],"perspective.":[113],"Our":[114,231],"proposal":[115],"called":[117],"Self-Supervised":[118],"Autoencoder--S2GAE,":[120],"which":[121],"unleashes":[122],"power":[124],"GAEs":[126],"with":[127,154],"minimal":[128],"yet":[129],"nontrivial":[130],"efforts.":[131],"Specifically,":[132],"instead":[133],"reconstructing":[135],"whole":[137],"input":[138],"structure,":[139],"randomly":[141],"mask":[142],"a":[143,225],"portion":[144],"edges":[146,153],"reconstruct":[150],"these":[151],"missing":[152],"strategy":[158],"expressive":[161],"decoder":[162],"network.":[163],"Moreover,":[164],"theoretically":[166],"prove":[167],"S2GAE":[169,210],"regarded":[172],"as":[173,224],"edge-level":[175],"contrastive":[176,215],"framework,":[178],"providing":[179],"insights":[180],"into":[181],"why":[182],"it":[183],"generalizes":[184],"well.":[185],"Empirically,":[186],"conduct":[188],"extensive":[189],"experiments":[190],"21":[192],"benchmark":[193],"datasets":[194],"across":[195],"&":[200],"The":[204],"results":[205],"validate":[206],"superiority":[208],"against":[211],"state-of-the-art":[212],"generative":[213],"methods.":[216],"study":[218],"demonstrates":[219],"potential":[221],"universal":[226],"representation":[227],"learner":[228],"graphs.":[230],"code":[232],"publicly":[234],"available":[235],"at":[236],"https://github.com/qiaoyu-tan/S2GAE.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":44},{"year":2024,"cited_by_count":43},{"year":2023,"cited_by_count":12}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}