{"id":"https://openalex.org/W7161848880","doi":"https://doi.org/10.48550/arxiv.2605.18893","title":"Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence","display_name":"Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence","publication_year":2026,"publication_date":"2026-05-17","ids":{"openalex":"https://openalex.org/W7161848880","doi":"https://doi.org/10.48550/arxiv.2605.18893"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.18893","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18893","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.2605.18893","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101981312","display_name":"Mridul Gupta","orcid":"https://orcid.org/0009-0003-4343-4263"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gupta, Mridul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127142581","display_name":"Samyak Jain","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jain, Samyak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113124272","display_name":"Vansh Ramani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramani, Vansh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017900329","display_name":"Hariprasad Kodamana","orcid":"https://orcid.org/0000-0003-3166-2712"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kodamana, Hariprasad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136528465","display_name":"Sayan Ranu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ranu, Sayan","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":0.9765999913215637,"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":0.9765999913215637,"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":0.00860000029206276,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0010999999940395355,"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/usable","display_name":"USable","score":0.6345999836921692},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5916000008583069},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48989999294281006},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36970001459121704},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35580000281333923},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3544999957084656},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.34700000286102295},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.3292999863624573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738000154495239},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6345999836921692},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5916000008583069},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47850000858306885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.475600004196167},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4262999892234802},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3181000053882599},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28850001096725464},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.18893","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18893","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.2605.18893","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18893","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":[0,34],"Neural":[1],"Networks":[2],"(GNNs)":[3],"are":[4,145,150,189],"powerful":[5],"tools":[6],"for":[7,175,186],"learning":[8],"from":[9,96],"graph-structured":[10],"data,":[11],"but":[12],"their":[13],"scalability":[14],"is":[15,114],"increasingly":[16],"strained":[17],"by":[18],"the":[19,37,47,53,63,77,82,87,115,209,216],"size":[20],"of":[21,39,49,66,89,219],"real-world":[22],"graphs":[23],"in":[24,166],"domains":[25],"like":[26],"recommender":[27],"systems,":[28],"fraud":[29],"detection,":[30],"and":[31,105,136,152,180,183,192,200,223],"molecular":[32],"biology.":[33],"condensation":[35,134],"--":[36,55,148],"task":[38],"generating":[40],"a":[41,59,70,171],"smaller":[42],"synthetic":[43],"graph":[44,164],"that":[45,163,188,213],"retains":[46],"performance":[48],"models":[50],"trained":[51],"on":[52,76,108,118,215],"original":[54],"has":[56],"emerged":[57],"as":[58,123],"promising":[60],"solution.":[61],"However,":[62],"dominant":[64],"approach":[65],"gradient":[67],"matching":[68],"introduces":[69],"fundamental":[71],"contradiction:":[72],"it":[73],"requires":[74],"training":[75,179,226],"full":[78],"dataset":[79],"to":[80,129,139,207],"create":[81],"compressed":[83],"version,":[84],"thereby":[85],"undermining":[86],"goal":[88],"efficiency.":[90],"Worse":[91],"still,":[92],"these":[93],"methods":[94,187],"suffer":[95],"high":[97],"computational":[98],"overhead,":[99,135],"poor":[100],"generalization":[101],"across":[102],"GNN":[103,225],"architectures,":[104],"brittle":[106],"reliance":[107,117],"specific":[109],"model":[110],"configurations.":[111],"Equally":[112],"concerning":[113],"community's":[116],"misleading":[119],"evaluation":[120],"protocols":[121],"such":[122],"node":[124],"compression":[125],"ratios,":[126],"which":[127],"fail":[128],"reflect":[130],"true":[131,217],"resource":[132],"savings,":[133],"illusory":[137],"application":[138],"neural":[140],"architecture":[141],"search.":[142],"These":[143],"shortcomings":[144],"not":[146],"incidental":[147],"they":[149,153],"systemic,":[151],"obstruct":[154],"meaningful":[155],"progress.":[156],"In":[157],"this":[158],"position":[159],"paper,":[160],"we":[161,205],"argue":[162],"condensation,":[165],"its":[167],"current":[168],"form,":[169],"needs":[170],"reset.":[172],"We":[173],"call":[174],"moving":[176],"beyond":[177],"full-dataset":[178],"model-dependent":[181],"design,":[182],"instead":[184],"advocate":[185],"lightweight,":[190],"architecture-agnostic,":[191],"practically":[193],"deployable.":[194],"By":[195],"identifying":[196],"key":[197],"methodological":[198],"flaws":[199],"outlining":[201],"concrete":[202],"research":[203],"directions,":[204],"aim":[206],"reorient":[208],"field":[210],"toward":[211],"approaches":[212],"deliver":[214],"promise":[218],"condensation:":[220],"efficient,":[221],"generalizable,":[222],"usable":[224],"at":[227],"scale.":[228]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-21T00:00:00"}