{"id":"https://openalex.org/W7162030396","doi":"https://doi.org/10.48550/arxiv.2605.20248","title":"Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification","display_name":"Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7162030396","doi":"https://doi.org/10.48550/arxiv.2605.20248"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20248","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20248","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.20248","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094208259","display_name":"Brown Zaz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zaz, Brown","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136726045","display_name":"Mar Gonz\u00e0lez I Catal\u00e0","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Catal\u00e0, Mar Gonz\u00e0lez I","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106113123","display_name":"Ferran Hernandez Caralt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caralt, Ferran Hernandez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064732307","display_name":"Moshe Eliasof","orcid":"https://orcid.org/0000-0002-1780-2312"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eliasof, Moshe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136714580","display_name":"Pietro Li\u00f2","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li\u00f2, Pietro","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":0.868399977684021,"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":0.868399977684021,"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":0.0272000003606081,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.018300000578165054,"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/graph","display_name":"Graph","score":0.5774000287055969},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4796000123023987},{"id":"https://openalex.org/keywords/sharpening","display_name":"Sharpening","score":0.46639999747276306},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4453999996185303},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4408000111579895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40299999713897705},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3564999997615814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253000140190125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5853999853134155},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C2781137444","wikidata":"https://www.wikidata.org/wiki/Q237105","display_name":"Sharpening","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4041000008583069},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3564999997615814},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20248","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20248","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.20248","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20248","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.656498908996582,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,28],"the":[1,5,36,80,107,154],"transductive":[2,45],"setting,":[3],"where":[4],"full":[6],"graph":[7],"is":[8,158],"observed":[9],"but":[10,66],"node":[11,20,51],"labels":[12,75],"are":[13,76],"only":[14],"partially":[15],"available,":[16],"progress":[17],"in":[18,106],"semi-supervised":[19],"classification":[21],"has":[22],"largely":[23],"focused":[24],"on":[25,123,130],"architectural":[26],"innovation.":[27],"this":[29,104,128],"paper,":[30],"we":[31,94],"revisit":[32],"an":[33],"orthogonal":[34],"axis:":[35],"training":[37,64],"objective.":[38],"We":[39,133],"start":[40],"from":[41],"a":[42,85,90,99,116,138],"simple":[43],"observation:":[44],"models":[46],"produce":[47],"predictions":[48,60],"for":[49],"every":[50],"during":[52],"training,":[53],"including":[54],"nodes":[55,125],"without":[56,149],"labels.":[57,110],"These":[58],"unlabeled-node":[59],"may":[61],"contain":[62],"useful":[63],"signal,":[65],"standard":[67],"supervised":[68],"objectives":[69],"discard":[70],"them":[71],"because":[72],"no":[73],"ground-truth":[74],"available.":[77],"Inspired":[78],"by":[79],"decomposition":[81],"of":[82,109,141],"cross-entropy":[83],"into":[84],"label-dependent":[86],"alignment":[87],"term":[88],"and":[89,144],"label-independent":[91],"entropy":[92,122],"term,":[93],"propose":[95],"prediction":[96,121],"confidence":[97],"as":[98],"natural":[100],"way":[101],"to":[102,153],"extract":[103],"signal":[105],"absence":[108],"This":[111],"motivates":[112],"Transductive":[113,135],"Sharpening":[114,136],"(TS):":[115],"loss-level":[117],"modification":[118],"that":[119],"minimizes":[120],"unlabeled":[124],"while":[126],"counterbalancing":[127],"effect":[129],"labeled":[131],"nodes.":[132],"evaluate":[134],"across":[137],"wide":[139],"range":[140],"node-classification":[142],"benchmarks":[143],"observe":[145],"consistent":[146],"performance":[147],"improvements":[148],"requiring":[150],"any":[151],"changes":[152],"backbone":[155],"architecture.":[156],"Code":[157],"available":[159],"at":[160],"https://github.com/transductive-sharpening/tunedGNN.":[161]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-22T00:00:00"}