{"id":"https://openalex.org/W7154116417","doi":"https://doi.org/10.48550/arxiv.2604.08553","title":"GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback","display_name":"GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7154116417","doi":"https://doi.org/10.48550/arxiv.2604.08553"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.08553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08553","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.08553","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113407873","display_name":"Ruiyao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xu, Ruiyao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133534375","display_name":"Kaize Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Kaize","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113407873"],"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":0.942300021648407,"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":0.942300021648407,"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/T10028","display_name":"Topic Modeling","score":0.03220000118017197,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.003599999938160181,"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/exploit","display_name":"Exploit","score":0.6541000008583069},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6243000030517578},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.532800018787384},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41040000319480896},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3375000059604645},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.31610000133514404}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6541000008583069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6535000205039978},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6243000030517578},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058000087738037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4812999963760376},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3375000059604645},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2759999930858612},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.25859999656677246},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.08553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08553","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.08553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08553","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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"strong":[6],"performance":[7],"on":[8,19,76,116,187],"text-attributed":[9],"graphs":[10],"(TAGs)":[11],"due":[12],"to":[13,84,159],"their":[14,24],"superior":[15],"semantic":[16],"understanding":[17],"ability":[18],"textual":[20],"node":[21],"features.":[22],"However,":[23],"effectiveness":[25],"as":[26],"predictors":[27],"in":[28,199],"the":[29,52,67,82,97,108,120,139,150,174,182],"low-resource":[30,200],"setting,":[31],"where":[32,202],"labeled":[33,48,145,203],"nodes":[34,143],"are":[35,205],"severely":[36],"limited":[37],"and":[38,71,80,152,157],"scarce,":[39],"remains":[40],"constrained":[41],"since":[42],"fine-tuning":[43,90,169],"LLMs":[44,91,111,156],"usually":[45],"requires":[46],"sufficient":[47],"data,":[49],"especially":[50],"when":[51,89],"TAG":[53,189],"shows":[54],"complex":[55],"structural":[56,121],"patterns.":[57],"In":[58],"essence,":[59],"this":[60],"paper":[61],"targets":[62],"two":[63],"key":[64],"challenges:":[65],"(i)":[66],"difficulty":[68],"of":[69,110,124],"generating":[70],"selecting":[72],"reliable":[73,161],"pseudo":[74,93,178],"labels":[75,179],"TAGs":[77,117],"for":[78,112],"LLMs,":[79],"(ii)":[81],"need":[83],"mitigate":[85],"potential":[86,183],"label":[87,184],"noise":[88],"with":[92],"labels.":[94,162],"To":[95],"counter":[96],"challenges,":[98],"we":[99,164],"propose":[100],"a":[101,132,166],"new":[102],"framework,":[103],"GNN-as-Judge,":[104],"which":[105],"can":[106,172],"unleash":[107],"power":[109],"few-shot":[113],"semi-supervised":[114],"learning":[115],"by":[118],"incorporating":[119],"inductive":[122],"bias":[123],"Graph":[125],"Neural":[126],"Networks":[127],"(GNNs).":[128],"Specifically,":[129],"GNN-as-Judge":[130,193],"introduces":[131],"collaborative":[133],"pseudo-labeling":[134],"strategy":[135],"that":[136,171,192],"first":[137],"identifies":[138],"most":[140],"influenced":[141],"unlabeled":[142],"from":[144,176],"nodes,":[146],"then":[147],"exploits":[148],"both":[149],"agreement":[151],"disagreement":[153],"patterns":[154],"between":[155],"GNNs":[158],"generate":[160],"Furthermore,":[163],"develop":[165],"weakly-supervised":[167],"LLM":[168],"algorithm":[170],"distill":[173],"knowledge":[175],"informative":[177],"while":[180],"mitigating":[181],"noise.":[185],"Experiments":[186],"multiple":[188],"datasets":[190],"demonstrate":[191],"significantly":[194],"outperforms":[195],"existing":[196],"methods,":[197],"particularly":[198],"regimes":[201],"data":[204],"scarce.":[206]},"counts_by_year":[],"updated_date":"2026-04-14T06:08:25.285971","created_date":"2026-04-14T00:00:00"}