{"id":"https://openalex.org/W4405094440","doi":"https://doi.org/10.48550/arxiv.2412.03864","title":"Training MLPs on Graphs without Supervision","display_name":"Training MLPs on Graphs without Supervision","publication_year":2024,"publication_date":"2024-12-05","ids":{"openalex":"https://openalex.org/W4405094440","doi":"https://doi.org/10.48550/arxiv.2412.03864"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2412.03864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03864","pdf_url":"https://arxiv.org/pdf/2412.03864","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.03864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062423029","display_name":"Zehong Wang","orcid":"https://orcid.org/0000-0002-7670-6777"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Zehong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691428","display_name":"Zheyuan Zhang","orcid":"https://orcid.org/0000-0002-1015-3700"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zheyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022275632","display_name":"Chuxu Zhang","orcid":"https://orcid.org/0000-0002-8349-7926"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chuxu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027601906","display_name":"Yanfang Ye","orcid":"https://orcid.org/0000-0002-6038-2173"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Yanfang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062423029"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9067000150680542,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9067000150680542,"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/training","display_name":"Training (meteorology)","score":0.4562479257583618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41359373927116394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37307852506637573},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3250040113925934},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1709158718585968},{"id":"https://openalex.org/keywords/meteorology","display_name":"Meteorology","score":0.046934276819229126}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4562479257583618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41359373927116394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37307852506637573},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3250040113925934},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1709158718585968},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.046934276819229126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2412.03864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03864","pdf_url":"https://arxiv.org/pdf/2412.03864","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.03864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.03864","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.03864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.03864","pdf_url":"https://arxiv.org/pdf/2412.03864","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1450250580","display_name":"CAREER: Securing Cyberspace: Gaining Deep Insights into the Online Underground Ecosystem","funder_award_id":"2203261","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1601924855","display_name":"III: Small: A New Machine Learning Paradigm Towards Effective yet Efficient Foundation Graph Learning Models","funder_award_id":"2321504","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2320213723","display_name":null,"funder_award_id":"2426514","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3087910168","display_name":"III: Medium: A Data-driven and AI-augmented Framework for Collaborative Decision Making to Combat Infectious Disease Outbreaks","funder_award_id":"2217239","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4590421986","display_name":null,"funder_award_id":"CMMI-2146076","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5954070948","display_name":null,"funder_award_id":"CMMI-","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6229722452","display_name":"EAGER: A New Explainable Multi-objective Learning Framework for Personalized Dietary Recommendations against Opioid Misuse and Addiction","funder_award_id":"2334193","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6745018468","display_name":null,"funder_award_id":"2146076","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8583216455","display_name":null,"funder_award_id":"IIS-2217239","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"},{"id":"https://openalex.org/F4320337391","display_name":"Division of Civil, Mechanical and Manufacturing Innovation","ror":"https://ror.org/028yd4c30"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405094440.pdf","grobid_xml":"https://content.openalex.org/works/W4405094440.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4,40],"demonstrated":[5],"their":[6,14],"effectiveness":[7],"in":[8,25,108,192],"various":[9],"graph":[10,126,182],"learning":[11,82,119,165],"tasks,":[12],"yet":[13],"reliance":[15],"on":[16,53,84,155,172],"neighborhood":[17,130],"aggregation":[18],"during":[19],"inference":[20],"poses":[21],"challenges":[22],"for":[23,81],"deployment":[24],"latency-sensitive":[26],"applications,":[27],"such":[28],"as":[29],"real-time":[30],"financial":[31],"fraud":[32],"detection.":[33],"To":[34,72],"address":[35],"this":[36,73],"limitation,":[37],"recent":[38],"studies":[39],"proposed":[41],"distilling":[42],"knowledge":[43],"from":[44],"teacher":[45],"GNNs":[46,107,128,153],"into":[47,93,139],"student":[48],"Multi-Layer":[49],"Perceptrons":[50],"(MLPs)":[51],"trained":[52],"node":[54,177,201],"content,":[55],"aiming":[56],"to":[57,87,106,116,120,184],"accelerate":[58],"inference.":[59],"However,":[60],"these":[61],"approaches":[62],"often":[63],"inadequately":[64],"explore":[65],"structural":[66,91,137,164,204],"information":[67,92,138,157],"when":[68],"inferring":[69],"unseen":[70,195],"nodes.":[71],"end,":[74],"we":[75,168],"introduce":[76],"SimMLP,":[77],"a":[78,143],"Self-supervised":[79],"framework":[80],"MLPs":[83],"graphs,":[85],"designed":[86],"fully":[88,134],"integrate":[89],"rich":[90],"MLPs.":[94,140],"Notably,":[95],"SimMLP":[96,151],"is":[97,115],"the":[98,109,122,136,148],"first":[99],"MLP-learning":[100],"method":[101],"that":[102],"can":[103],"achieve":[104],"equivalence":[105,149],"optimal":[110],"case.":[111],"The":[112],"key":[113],"idea":[114],"employ":[117],"self-supervised":[118],"align":[121],"representations":[123],"encoded":[124],"by":[125],"context-aware":[127],"and":[129,152,158,181,199],"dependency-free":[131],"MLPs,":[132],"thereby":[133],"integrating":[135],"We":[141],"provide":[142],"comprehensive":[144],"theoretical":[145],"analysis,":[146],"demonstrating":[147],"between":[150],"based":[154],"mutual":[156],"inductive":[159,198],"bias,":[160],"highlighting":[161],"SimMLP's":[162,186],"advanced":[163],"capabilities.":[166],"Additionally,":[167],"conduct":[169],"extensive":[170],"experiments":[171],"20":[173],"benchmark":[174],"datasets,":[175],"covering":[176],"classification,":[178,183],"link":[179],"prediction,":[180],"showcase":[185],"superiority":[187],"over":[188],"state-of-the-art":[189],"baselines,":[190],"particularly":[191],"scenarios":[193],"involving":[194],"nodes":[196],"(e.g.,":[197],"cold-start":[200],"classification)":[202],"where":[203],"insights":[205],"are":[206,210],"crucial.":[207],"Our":[208],"codes":[209],"available":[211],"at:":[212],"https://github.com/Zehong-Wang/SimMLP.":[213]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}