{"id":"https://openalex.org/W7166006125","doi":"https://doi.org/10.48550/arxiv.2606.26662","title":"Zero-Shot Size Transfer for Neural ODEs on Sparse Random Graphs: Graphon Limits and Adjoint Convergence","display_name":"Zero-Shot Size Transfer for Neural ODEs on Sparse Random Graphs: Graphon Limits and Adjoint Convergence","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166006125","doi":"https://doi.org/10.48550/arxiv.2606.26662"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.26662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26662","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.2606.26662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139447270","display_name":"Mingsong Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Mingsong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139441150","display_name":"Zhida Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhida","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078840209","display_name":"Sui Tang","orcid":"https://orcid.org/0000-0003-3284-5123"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Sui","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":0.9782000184059143,"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":0.9782000184059143,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.0015999999595806003,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.7529000043869019},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.5996999740600586},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5210999846458435},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.515500009059906},{"id":"https://openalex.org/keywords/ordinary-differential-equation","display_name":"Ordinary differential equation","score":0.49810001254081726},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.4837000072002411},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.475600004196167},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.44350001215934753}],"concepts":[{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.7529000043869019},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6100000143051147},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5996999740600586},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5356000065803528},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5210999846458435},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C51544822","wikidata":"https://www.wikidata.org/wiki/Q465274","display_name":"Ordinary differential equation","level":3,"score":0.49810001254081726},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.3971000015735626},{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C47458327","wikidata":"https://www.wikidata.org/wiki/Q910404","display_name":"Random graph","level":3,"score":0.33640000224113464},{"id":"https://openalex.org/C57945734","wikidata":"https://www.wikidata.org/wiki/Q7977941","display_name":"Weak convergence","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C181789720","wikidata":"https://www.wikidata.org/wiki/Q4812191","display_name":"Asymptotically optimal algorithm","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C75380026","wikidata":"https://www.wikidata.org/wiki/Q868454","display_name":"Euler method","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C62884695","wikidata":"https://www.wikidata.org/wiki/Q184871","display_name":"Euler's formula","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.26662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26662","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.2606.26662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26662","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":[0,16],"Neural":[1,11,17,59],"Differential":[2,60],"Equations":[3,61],"(GNDEs)":[4],"model":[5],"continuous-time":[6],"graph":[7,32,84],"dynamics":[8],"by":[9],"parameterizing":[10],"ODE":[12],"velocity":[13],"fields":[14],"with":[15,85,107,137,149],"Networks.":[18],"Their":[19],"local,":[20],"size-independent":[21],"filters":[22],"suggest":[23],"a":[24,30,43],"zero-shot":[25,178],"size-transfer":[26],"principle:":[27],"train":[28],"on":[29,35,49,168,191],"small":[31],"and":[33,63,73,77,121,129,144,151,158,164,170],"deploy":[34],"larger,":[36],"similar":[37],"graphs":[38,52],"without":[39],"retraining.":[40],"We":[41,56,110,124],"develop":[42],"quantitative":[44],"theory":[45],"for":[46,116],"this":[47],"principle":[48],"sparse":[50],"random":[51,83],"sampled":[53,194],"from":[54],"graphons.":[55],"consider":[57],"Graphon":[58],"(Graphon-NDEs)":[62],"adjoint":[64,74,117],"Graphon-NDEs":[65],"as":[66],"the":[67,71,174],"infinite-node":[68],"limits":[69],"of":[70,93,155,188],"forward":[72],"GNDE":[75,94],"systems,":[76],"establish":[78,112],"well-posedness.":[79],"For":[80],"an":[81],"$n$-node":[82],"sparsity":[86,163],"parameter":[87,122],"$\u03b1_n$,":[88],"we":[89,140],"prove":[90],"trajectory-wise":[91],"convergence":[92,114],"solutions":[95,98],"to":[96,104,162],"Graphon-NDE":[97],"at":[99],"rate":[100],"$O((\u03b1_n":[101],"n)^{-1/2})$,":[102],"up":[103,161],"logarithmic":[105,165],"factors,":[106],"high":[108],"probability.":[109],"also":[111],"uniform-in-time":[113],"bounds":[115],"systems":[118],"governing":[119],"hidden-state":[120,150],"gradients.":[123],"further":[125],"study":[126],"discretize-then-optimize":[127],"(DTO)":[128],"optimize-then-discretize":[130],"(OTD)":[131],"training.":[132],"Under":[133],"explicit":[134],"Euler":[135],"discretization":[136],"$M$":[138],"steps,":[139],"show":[141],"that":[142],"DTO":[143],"OTD":[145],"are":[146],"asymptotically":[147],"consistent,":[148],"local":[152],"parameter-gradient":[153],"discrepancies":[154],"orders":[156],"$O(1/M)$":[157],"$O(1/M^2)$,":[159],"respectively,":[160],"factors.":[166],"Experiments":[167],"HSBM":[169],"tent":[171],"graphons":[172],"support":[173],"theoretical":[175],"rates,":[176],"while":[177],"transfer":[179],"experiments":[180],"across":[181],"four":[182],"graphon":[183],"classes":[184],"demonstrate":[185],"accurate":[186],"deployment":[187],"learned":[189],"GNDEs":[190],"larger":[192],"independently":[193],"graphs.":[195]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-27T00:00:00"}