{"id":"https://openalex.org/W4416355784","doi":"https://doi.org/10.48550/arxiv.2511.12601","title":"Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization","display_name":"Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization","publication_year":2025,"publication_date":"2025-11-16","ids":{"openalex":"https://openalex.org/W4416355784","doi":"https://doi.org/10.48550/arxiv.2511.12601"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2511.12601","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.12601","pdf_url":"https://arxiv.org/pdf/2511.12601","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.12601","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120505793","display_name":"Odysseas Boufalis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boufalis, Odysseas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120505794","display_name":"Jorge Carrasco-Pollo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carrasco-Pollo, Jorge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001564251","display_name":"Joshua J. C. Rosenthal","orcid":"https://orcid.org/0000-0001-8139-9364"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rosenthal, Joshua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120411171","display_name":"Eduardo Terres-Caballero","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Terres-Caballero, Eduardo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120411172","display_name":"Alejandro Garc\u00eda-Castellanos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garc\u00eda-Castellanos, Alejandro","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":0.9380999803543091,"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":0.9380999803543091,"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":0.011900000274181366,"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":0.007899999618530273,"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/permutation","display_name":"Permutation (music)","score":0.5690000057220459},{"id":"https://openalex.org/keywords/homogeneous-space","display_name":"Homogeneous space","score":0.5572999715805054},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5550000071525574},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.491100013256073},{"id":"https://openalex.org/keywords/equivariant-map","display_name":"Equivariant map","score":0.4799000024795532},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.46860000491142273},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.44600000977516174},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4147000014781952}],"concepts":[{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5690000057220459},{"id":"https://openalex.org/C96469262","wikidata":"https://www.wikidata.org/wiki/Q1324364","display_name":"Homogeneous space","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5550000071525574},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45890000462532043},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4390000104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4235000014305115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41990000009536743},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C20295870","wikidata":"https://www.wikidata.org/wiki/Q5532500","display_name":"Generalized permutation matrix","level":4,"score":0.4034999907016754},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.35600000619888306},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C53811970","wikidata":"https://www.wikidata.org/wiki/Q5062194","display_name":"Centrality","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C39891107","wikidata":"https://www.wikidata.org/wiki/Q5767098","display_name":"Hinge loss","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.12601","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.12601","pdf_url":"https://arxiv.org/pdf/2511.12601","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.12601","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.12601","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.12601","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.12601","pdf_url":"https://arxiv.org/pdf/2511.12601","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Neural":[0,95,100],"network":[1],"parameterizations":[2],"exhibit":[3],"inherent":[4],"symmetries":[5,22,44,56,108],"that":[6,53,90,118],"yield":[7],"multiple":[8],"equivalent":[9],"minima":[10],"within":[11,123],"the":[12,112,124],"loss":[13,64],"landscape.":[14],"Scale":[15],"Graph":[16],"Metanetworks":[17],"(ScaleGMNs)":[18],"explicitly":[19,110],"leverage":[20],"these":[21],"by":[23,37,73],"proposing":[24],"an":[25,79],"architecture":[26],"equivariant":[27],"to":[28],"both":[29,104],"permutation":[30,43,55,105],"and":[31,98,106],"parameter":[32],"scaling":[33,76,107],"transformations.":[34],"Previous":[35],"work":[36],"Ainsworth":[38],"et":[39],"al.":[40],"(2023)":[41],"addressed":[42],"through":[45],"a":[46,62],"computationally":[47],"intensive":[48],"combinatorial":[49],"assignment":[50,113],"problem,":[51],"demonstrating":[52],"leveraging":[54],"alone":[57],"can":[58],"map":[59],"networks":[60,120],"into":[61],"shared":[63],"basin.":[65],"In":[66],"this":[67],"work,":[68],"we":[69],"extend":[70],"their":[71],"approach":[72,116],"also":[74],"incorporating":[75],"symmetries,":[77],"presenting":[78],"autoencoder":[80],"framework":[81],"utilizing":[82],"ScaleGMNs":[83],"as":[84],"invariant":[85],"encoders.":[86],"Experimental":[87],"results":[88],"demonstrate":[89],"our":[91,146],"method":[92],"aligns":[93],"Implicit":[94],"Representations":[96],"(INRs)":[97],"Convolutional":[99],"Networks":[101],"(CNNs)":[102],"under":[103],"without":[109],"solving":[111],"problem.":[114],"This":[115],"ensures":[117],"similar":[119],"naturally":[121],"converge":[122],"same":[125],"basin,":[126],"facilitating":[127],"model":[128],"merging,":[129],"i.e.,":[130],"smooth":[131],"linear":[132],"interpolation":[133],"while":[134],"avoiding":[135],"regions":[136],"of":[137],"high":[138],"loss.":[139],"The":[140],"code":[141],"is":[142],"publicly":[143],"available":[144],"on":[145],"GitHub":[147],"repository.":[148]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-11-19T00:00:00"}