{"id":"https://openalex.org/W7130328255","doi":"https://doi.org/10.1007/s11063-026-11833-6","title":"Revisiting Graph Learning Benchmarks: When is the Graph Actually Necessary?","display_name":"Revisiting Graph Learning Benchmarks: When is the Graph Actually Necessary?","publication_year":2026,"publication_date":"2026-02-18","ids":{"openalex":"https://openalex.org/W7130328255","doi":"https://doi.org/10.1007/s11063-026-11833-6"},"language":"en","primary_location":{"id":"doi:10.1007/s11063-026-11833-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-026-11833-6","pdf_url":null,"source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s11063-026-11833-6","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114657099","display_name":"Isay Katsman","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Isay Katsman","raw_affiliation_strings":["Applied Mathematics, Yale University, New Haven, 06520, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Mathematics, Yale University, New Haven, 06520, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115714083","display_name":"Ethan Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ethan Lou","raw_affiliation_strings":["Yale College, Yale University, New Haven, 06520, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale College, Yale University, New Haven, 06520, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042502878","display_name":"Anna C. Gilbert","orcid":"https://orcid.org/0000-0002-9627-9274"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Gilbert","raw_affiliation_strings":["Electrical Engineering, Yale University, New Haven, 06520, CT, USA","Statistics & Data Science, Yale University, New Haven, 06520, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering, Yale University, New Haven, 06520, CT, USA","institution_ids":["https://openalex.org/I32971472"]},{"raw_affiliation_string":"Statistics & Data Science, Yale University, New Haven, 06520, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5114657099"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19760186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"58","issue":"2","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":0.9646999835968018,"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":0.9646999835968018,"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":0.004999999888241291,"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/T13702","display_name":"Machine Learning in Healthcare","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/graph-property","display_name":"Graph property","score":0.5073999762535095},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5041999816894531},{"id":"https://openalex.org/keywords/graph-kernel","display_name":"Graph kernel","score":0.40230000019073486},{"id":"https://openalex.org/keywords/voltage-graph","display_name":"Voltage graph","score":0.38179999589920044},{"id":"https://openalex.org/keywords/graph-database","display_name":"Graph database","score":0.3806000053882599},{"id":"https://openalex.org/keywords/clique-width","display_name":"Clique-width","score":0.3727000057697296},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.3628999888896942},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.3610000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6498000025749207},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5482000112533569},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.5073999762535095},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C100595998","wikidata":"https://www.wikidata.org/wiki/Q11731931","display_name":"Graph kernel","level":5,"score":0.40230000019073486},{"id":"https://openalex.org/C22149727","wikidata":"https://www.wikidata.org/wiki/Q7940747","display_name":"Voltage graph","level":4,"score":0.38179999589920044},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.3806000053882599},{"id":"https://openalex.org/C5737132","wikidata":"https://www.wikidata.org/wiki/Q1101814","display_name":"Clique-width","level":5,"score":0.3727000057697296},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3628999888896942},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C17169500","wikidata":"https://www.wikidata.org/wiki/Q3033506","display_name":"Null graph","level":5,"score":0.3490999937057495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C148067565","wikidata":"https://www.wikidata.org/wiki/Q3323718","display_name":"Moral graph","level":5,"score":0.2955000102519989},{"id":"https://openalex.org/C134727501","wikidata":"https://www.wikidata.org/wiki/Q5597073","display_name":"Graph bandwidth","level":5,"score":0.2921999990940094},{"id":"https://openalex.org/C36382193","wikidata":"https://www.wikidata.org/wiki/Q7068966","display_name":"Null model","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C168291704","wikidata":"https://www.wikidata.org/wiki/Q902252","display_name":"Complement graph","level":5,"score":0.2777999937534332},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.27559998631477356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11063-026-11833-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-026-11833-6","pdf_url":null,"source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11063-026-11833-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-026-11833-6","pdf_url":null,"source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4998723566532135}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308380","display_name":"Yale University","ror":"https://ror.org/03v76x132"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1981666390","https://openalex.org/W1983320747","https://openalex.org/W2112090702","https://openalex.org/W2128678576","https://openalex.org/W2153959628","https://openalex.org/W2166681504","https://openalex.org/W2199357291","https://openalex.org/W2558460151","https://openalex.org/W2558748708","https://openalex.org/W2791194998","https://openalex.org/W2809638236","https://openalex.org/W2907492528","https://openalex.org/W3035965352","https://openalex.org/W3042770487","https://openalex.org/W3139306118","https://openalex.org/W3164410012"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Graph":[1],"machine":[2],"learning":[3,16,41,132,156],"has":[4],"enjoyed":[5],"a":[6,119,182,220,239],"meteoric":[7],"rise":[8],"in":[9,17,31,38,88,205],"popularity":[10],"since":[11],"the":[12,26,44,47,60,127,158,171,174,191,197],"introduction":[13],"of":[14,28,46,65,126,207,212,224,241],"deep":[15],"graph":[18,29,40,48,61,89,110,131,140,155,164,215,230,259],"contexts.":[19],"This":[20],"is":[21,43,71],"no":[22],"surprise":[23],"due":[24],"to":[25,166],"ubiquity":[27],"data":[30,58],"large":[32],"scale":[33],"industrial":[34],"settings.":[35],"Tacitly":[36],"assumed":[37],"all":[39],"tasks":[42],"separation":[45],"structure":[49,62,141],"and":[50,188,201,252],"node":[51,53,73,102],"features:":[52],"features":[54,74,103,159,192],"strictly":[55],"encode":[56],"individual":[57],"while":[59],"consists":[63],"only":[64],"pairwise":[66],"interactions.":[67],"The":[68],"driving":[69],"belief":[70],"that":[72,147,228,244],"are":[75,104,193,245],"(by":[76],"themselves)":[77],"insufficient":[78],"for":[79,107,173,195,214,232,258],"these":[80,148,186],"tasks,":[81],"so":[82],"benchmark":[83],"performance":[84],"accurately":[85],"reflects":[86],"improvements":[87],"learning.":[90],"In":[91],"our":[92],"paper,":[93],"we":[94,180,218,236],"challenge":[95],"this":[96,113,178],"orthodoxy":[97],"by":[98,249],"showing":[99],"that,":[100],"surprisingly,":[101],"oftentimes":[105],"more-than-sufficient":[106],"many":[108],"common":[109],"benchmarks,":[111],"breaking":[112],"critical":[114],"assumption.":[115],"When":[116],"comparing":[117],"against":[118],"well-tuned":[120],"feature-only":[121],"MLP":[122,200,251],"baseline":[123],"on":[124,142,185],"seven":[125],"most":[128],"commonly":[129],"used":[130],"datasets,":[133],"one":[134],"gains":[135],"little":[136],"benefit":[137,152],"from":[138,154],"using":[139],"five":[143],"datasets.":[144],"We":[145],"posit":[146],"datasets":[149,187,227,243],"do":[150],"not":[151,246],"considerably":[153],"because":[157],"themselves":[160],"already":[161],"contain":[162],"enough":[163],"information":[165,231],"obviate":[167],"or":[168],"substantially":[169],"reduce":[170],"need":[172],"graph.":[175],"To":[176],"illustrate":[177],"point,":[179],"perform":[181],"feature":[183],"study":[184],"show":[189],"how":[190],"responsible":[194],"closing":[196],"gap":[198],"between":[199],"graph-method":[202],"performance.":[203,234],"Further,":[204],"service":[206],"introducing":[208],"better":[209],"empirical":[210],"measures":[211],"progress":[213],"neural":[216,260],"networks,":[217],"present":[219],"challenging":[221],"parametric":[222],"family":[223],"principled":[225],"synthetic":[226],"necessitate":[229],"nontrivial":[233],"Lastly,":[235],"section":[237],"out":[238],"subset":[240],"real-world":[242],"trivially":[247],"solved":[248],"an":[250],"hence":[253],"serve":[254],"as":[255],"reasonable":[256],"benchmarks":[257],"networks.":[261]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-02-19T00:00:00"}