{"id":"https://openalex.org/W7162399747","doi":"https://doi.org/10.48550/arxiv.2605.25662","title":"Closed-Form Node Classification with Exact Graph Unlearning","display_name":"Closed-Form Node Classification with Exact Graph Unlearning","publication_year":2026,"publication_date":"2026-05-25","ids":{"openalex":"https://openalex.org/W7162399747","doi":"https://doi.org/10.48550/arxiv.2605.25662"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.25662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25662","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2605.25662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137024098","display_name":"Aditya Gaur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaur, Aditya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137028379","display_name":"Charu Sharma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharma, Charu","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":0.9936000108718872,"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":0.9936000108718872,"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":0.0010999999940395355,"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":0.0005000000237487257,"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":0.505299985408783},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.482699990272522},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.46630001068115234},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4648999869823456},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4404999911785126},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.3968999981880188},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.3797000050544739},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.3783000111579895},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3497999906539917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5396000146865845},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49059998989105225},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.46630001068115234},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4205999970436096},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.3968999981880188},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3783000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3553999960422516},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C32277403","wikidata":"https://www.wikidata.org/wiki/Q740445","display_name":"Ridge","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C17169500","wikidata":"https://www.wikidata.org/wiki/Q3033506","display_name":"Null graph","level":5,"score":0.25760000944137573},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.2522999942302704},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.25662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25662","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2605.25662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25662","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0],"neural":[1],"networks":[2],"for":[3,81,199,210],"node":[4],"classification":[5],"are":[6,97,177],"typically":[7],"trained":[8],"by":[9,50,67,78,99],"gradient":[10,234],"descent":[11],"over":[12,226,233],"hundreds":[13],"or":[14,115],"thousands":[15],"of":[16,44,124,138,180,243,250],"epochs.":[17],"Recent":[18],"work":[19],"has":[20],"shown":[21],"that,":[22],"when":[23],"properly":[24],"tuned,":[25],"classic":[26],"GCN/SAGE/GAT":[27,121],"architectures":[28],"can":[29,47,187],"match":[30,114],"graph":[31,90,185],"transformers":[32],"on":[33,122,136,148],"many":[34],"node-classification":[35],"benchmarks.":[36],"We":[37,60,194],"ask":[38],"a":[39,62,87,100],"complementary":[40],"question:":[41],"how":[42],"much":[43],"this":[45,58],"performance":[46],"be":[48,188],"recovered":[49],"deterministic":[51,181],"closed-form":[52,64,89,112],"solvers,":[53],"and":[54,109,142,204,213,229,246],"what":[55],"guarantees":[56],"does":[57],"enable?":[59],"introduce":[61,85],"routed":[63],"framework":[65],"selected":[66],"adjusted":[68],"homophily.":[69],"For":[70],"assortative":[71],"graphs,":[72,83],"we":[73,84],"use":[74],"SGC-style":[75],"propagation":[76],"followed":[77],"Ridge":[79,95,211],"regression;":[80],"heterophilous":[82,154],"LCF-Net,":[86],"layer-wise":[88],"feature-refinement":[91],"network":[92],"whose":[93],"per-layer":[94],"solves":[96],"capped":[98],"Gaussian":[101],"kernel-Ridge":[102],"head.":[103],"Across":[104],"14":[105],"benchmarks,":[106,141],"including":[107],"ogbn-arxiv":[108],"ogbn-proteins,":[110],"our":[111,175],"predictors":[113,176],"beat":[116],"the":[117,144,158,168,240,247],"best":[118],"vanilla":[119,161],"2-layer":[120,162],"9":[123,125,137],"measured":[126],"datasets,":[127],"tie":[128],"tuned":[129],"deep":[130,164],"recipes":[131],"within":[132],"one":[133],"standard":[134],"deviation":[135],"12":[139],"small":[140],"exceed":[143],"OGB-leaderboard":[145],"plain":[146],"GCN":[147],"both":[149],"large":[150],"graphs.":[151],"The":[152],"remaining":[153],"gap":[155],"closely":[156],"tracks":[157],"gain":[159],"from":[160],"to":[163,190],"SAGE,":[165],"suggesting":[166],"that":[167],"residual":[169],"difference":[170],"is":[171],"primarily":[172],"architectural.":[173],"Because":[174],"explicit":[178],"solutions":[179],"linear":[182],"systems,":[183],"modified":[184],"inputs":[186],"re-solved":[189],"obtain":[191],"retrain-equivalent":[192],"parameters.":[193],"formalize":[195],"exact":[196,244],"graph-object":[197],"unlearning":[198],"label,":[200],"feature,":[201],"edge,":[202],"node,":[203],"subgraph":[205],"modifications,":[206],"prove":[207],"K-hop":[208],"locality":[209],"components,":[212],"verify":[214],"exactness":[215],"across":[216],"109":[217],"configurations.":[218],"On":[219],"ogbn-arxiv,":[220],"localized":[221],"updates":[222],"give":[223],"$21$--$45\\times$":[224],"speedups":[225,232],"full":[227],"re-solving":[228],"roughly":[230],"$10^{6}\\times$":[231],"retraining.":[235],"Structural-inversion":[236],"experiments":[237],"further":[238],"quantify":[239],"privacy":[241],"floor":[242],"retraining":[245],"additional":[248],"leakage":[249],"approximate":[251],"graph-unlearning":[252],"methods.":[253]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-27T00:00:00"}