{"id":"https://openalex.org/W7161687451","doi":"https://doi.org/10.48550/arxiv.2605.17854","title":"Learning over Positive and Negative Edges with Contrastive Message Passing","display_name":"Learning over Positive and Negative Edges with Contrastive Message Passing","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7161687451","doi":"https://doi.org/10.48550/arxiv.2605.17854"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.17854","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17854","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.17854","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020916103","display_name":"Peter Pao-Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pao-Huang, Peter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034936665","display_name":"Charilaos I. Kanatsoulis","orcid":"https://orcid.org/0000-0002-0952-1561"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kanatsoulis, Charilaos I.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022990159","display_name":"Michael Bereket","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bereket, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136497086","display_name":"Jure Leskovec","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leskovec, Jure","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.992900013923645,"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":0.992900013923645,"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":0.002099999925121665,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.000699999975040555,"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/message-passing","display_name":"Message passing","score":0.7825999855995178},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5536999702453613},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.47380000352859497},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4471000134944916},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39070001244544983},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.33250001072883606}],"concepts":[{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.7825999855995178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662999987602234},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5504000186920166},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34450000524520874},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3375999927520752},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C152948882","wikidata":"https://www.wikidata.org/wiki/Q4060686","display_name":"Belief propagation","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2597000002861023},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.17854","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17854","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.17854","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17854","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"approaches":[1,20],"to":[2,14,63,96,119,126],"learning":[3],"on":[4,109],"graphs":[5],"involve":[6],"message":[7,87],"passing":[8,88],"along":[9],"existing":[10],"(i.e.,":[11,31],"positive)":[12],"edges":[13,43,65,148],"update":[15],"node":[16],"features.":[17],"However,":[18],"these":[19],"often":[21],"disregard":[22],"the":[23,29,39,110],"potentially":[24],"valuable":[25],"information":[26,68],"contained":[27],"in":[28,44,50,135,143],"absence":[30],"negative)":[32],"of":[33,41,52],"edges.":[34,74,102],"Here,":[35],"we":[36,79],"theoretically":[37],"analyze":[38],"value":[40],"negative":[42,64,101,147],"graph":[45,92],"representations":[46],"and":[47,58,100,123,132],"prove":[48],"that":[49,90],"settings":[51,145],"low":[53],"label":[54],"rates,":[55],"high":[56,59],"homophily,":[57],"edge":[60],"density,":[61],"access":[62],"provides":[66],"significant":[67],"gain":[69],"over":[70,98],"using":[71],"only":[72],"positive":[73,99,106],"Motivated":[75],"by":[76],"this":[77],"insight,":[78],"introduce":[80],"Contrastive":[81],"Message":[82],"Passing":[83],"(CMP),":[84],"a":[85],"general":[86],"architecture":[89],"enable":[91],"neural":[93],"network":[94],"layers":[95],"reason":[97],"By":[103],"imposing":[104],"soft":[105],"semidefinite":[107],"constraints":[108],"learnable":[111],"weights,":[112],"our":[113],"approach":[114],"differentially":[115],"applies":[116],"similarity-preserving":[117],"transformations":[118,125],"positively":[120],"connected":[121,128],"nodes":[122],"dissimilarity-inducing":[124],"negatively":[127],"nodes.":[129],"Over":[130],"simulated":[131],"real":[133],"datasets":[134],"varying":[136],"data":[137],"regimes,":[138],"CMP":[139],"consistently":[140],"outperforms":[141],"baselines":[142],"low-label":[144],"when":[146],"are":[149],"informative.":[150]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-20T00:00:00"}