{"id":"https://openalex.org/W7133518294","doi":"https://doi.org/10.48550/arxiv.2603.02938","title":"Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models","display_name":"Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133518294","doi":"https://doi.org/10.48550/arxiv.2603.02938"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.02938","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02938","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.2603.02938","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045862030","display_name":"Fengzhi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Fengzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128046156","display_name":"Liang Zhang (41392)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103762922","display_name":"Yuan Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128081935","display_name":"Ruiqing Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Ruiqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128101971","display_name":"YanSong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, YanSong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128099785","display_name":"Yunfei Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Yunfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128048379","display_name":"Fanyu Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Fanyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128118238","display_name":"Junlan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Junlan","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":0.9564999938011169,"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":0.9564999938011169,"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":0.015300000086426735,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.0031999999191612005,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.5558000206947327},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4481000006198883},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.3950999975204468},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.38920000195503235},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.322299987077713},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3043000102043152},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.2964000105857849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024999856948853},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5457000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4034999907016754},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C198386975","wikidata":"https://www.wikidata.org/wiki/Q117785","display_name":"Finite impulse response","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.02938","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02938","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.2603.02938","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02938","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":{"Graph-based":[0],"tasks":[1],"in":[2,125],"the":[3,15,61,99,133,149,159,202,219],"zero-shot":[4,78,126],"setting":[5],"remain":[6],"a":[7,67,83,115,145,169,189],"significant":[8,92],"challenge":[9],"due":[10],"to":[11,23,25,44,105,141,151,221],"data":[12,170],"scarcity":[13],"and":[14,71,96,103,123,157,198,214],"inability":[16],"of":[17,183],"traditional":[18],"Graph":[19],"Neural":[20],"Networks":[21],"(GNNs)":[22],"generalize":[24],"unseen":[26],"domains":[27],"or":[28],"label":[29],"spaces.":[30],"While":[31],"recent":[32,56],"advancements":[33],"have":[34],"transitioned":[35],"toward":[36],"leveraging":[37],"Large":[38],"Language":[39],"Models":[40],"(LLMs)":[41],"as":[42],"predictors":[43],"enhance":[45],"GNNs,":[46],"these":[47],"methods":[48],"often":[49],"suffer":[50],"from":[51],"cross-modal":[52],"alignment":[53],"issues.":[54],"A":[55],"paradigm":[57],"(i.e.,":[58],"Graph-R1)":[59],"overcomes":[60],"aforementioned":[62],"architectural":[63],"dependencies":[64],"by":[65],"adopting":[66],"purely":[68],"text-based":[69],"format":[70],"utilizing":[72],"LLM-based":[73,127],"graph":[74,128,177],"reasoning,":[75],"showing":[76],"improved":[77],"generalization.":[79],"However,":[80],"it":[81],"employs":[82],"task-agnostic,":[84],"one-size-fits-all":[85,160],"subgraph":[86,121,139,209],"extraction":[87,122,140],"strategy,":[88],"which":[89,136],"inevitably":[90],"introduces":[91],"structural":[93],"noise--irrelevant":[94],"neighbors":[95,156],"edges--that":[97],"distorts":[98],"LLMs'":[100],"receptive":[101],"field":[102],"leads":[104],"suboptimal":[106],"predictions.":[107],"To":[108,162],"address":[109],"this":[110,164],"limitation,":[111],"we":[112,131,166,186,217],"introduce":[113],"GraphSSR,":[114],"novel":[116],"framework":[117,193],"designed":[118,206],"for":[119,180,207,229],"adaptive":[120,208],"denoising":[124],"reasoning.":[129,230],"Specifically,":[130],"propose":[132,187],"SSR":[134,204],"pipeline,":[135],"dynamically":[137],"tailors":[138],"specific":[142],"contexts":[143],"through":[144],"\"Sample-Select-Reason\"":[146],"process,":[147],"enabling":[148],"model":[150,220],"autonomously":[152],"filter":[153],"out":[154],"task-irrelevant":[155],"overcome":[158],"issue.":[161],"internalize":[163],"capability,":[165],"develop":[167],"SSR-SFT,":[168],"synthesis":[171],"strategy":[172],"that":[173,194],"generates":[174],"high-quality":[175],"SSR-style":[176],"reasoning":[178],"traces":[179],"supervised":[181],"fine-tuning":[182],"LLMs.":[184],"Furthermore,":[185],"SSR-RL,":[188],"two-stage":[190],"reinforcement":[191],"learning":[192],"explicitly":[195],"regulates":[196],"sampling":[197],"selection":[199],"operations":[200],"within":[201],"proposed":[203],"pipeline":[205],"denoising.":[210],"By":[211],"incorporating":[212],"Authenticity-Reinforced":[213],"Denoising-Reinforced":[215],"RL,":[216],"guide":[218],"achieve":[222],"accurate":[223],"predictions":[224],"using":[225],"parsimonious,":[226],"denoised":[227],"subgraphs":[228]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-05T00:00:00"}