{"id":"https://openalex.org/W7167581049","doi":"https://doi.org/10.48550/arxiv.2607.03798","title":"Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks","display_name":"Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks","publication_year":2026,"publication_date":"2026-07-04","ids":{"openalex":"https://openalex.org/W7167581049","doi":"https://doi.org/10.48550/arxiv.2607.03798"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.03798","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03798","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.2607.03798","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140167344","display_name":"Yoshihiro Maruyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Maruyama, Yoshihiro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5140167344"],"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":0.7985000014305115,"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":0.7985000014305115,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.1005999967455864,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.012799999676644802,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/equivariant-map","display_name":"Equivariant map","score":0.8205000162124634},{"id":"https://openalex.org/keywords/sheaf","display_name":"Sheaf","score":0.7402999997138977},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6574000120162964},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5246999859809875},{"id":"https://openalex.org/keywords/homogeneous-space","display_name":"Homogeneous space","score":0.4742000102996826},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.44269999861717224},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4214000105857849},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4185999929904938}],"concepts":[{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.8205000162124634},{"id":"https://openalex.org/C4017995","wikidata":"https://www.wikidata.org/wiki/Q595298","display_name":"Sheaf","level":2,"score":0.7402999997138977},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6574000120162964},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48840001225471497},{"id":"https://openalex.org/C96469262","wikidata":"https://www.wikidata.org/wiki/Q1324364","display_name":"Homogeneous space","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3752000033855438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36649999022483826},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3357999920845032},{"id":"https://openalex.org/C2779886137","wikidata":"https://www.wikidata.org/wiki/Q21030012","display_name":"Symmetry (geometry)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.31779998540878296},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C93067474","wikidata":"https://www.wikidata.org/wiki/Q1493952","display_name":"Sheaf cohomology","level":4,"score":0.26249998807907104},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.2549000084400177},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.03798","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03798","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.2607.03798","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03798","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":{"Symmetry":[0],"is":[1],"everywhere":[2],"in":[3,183],"nature":[4],"and":[5,25,40,60,88,116,185],"society.":[6],"Geometric":[7],"deep":[8,17,34,45,188],"learning":[9,18,35,189],"builds":[10],"architectures":[11],"respecting":[12],"group":[13,38],"symmetries,":[14],"whereas":[15],"topological":[16,44],"organizes":[19],"computation":[20],"through":[21],"cells,":[22],"incidence":[23],"relations,":[24],"local-to-global":[26],"structure.":[27],"In":[28,146],"this":[29],"paper,":[30],"we":[31,48,149],"extend":[32],"geometric":[33,187],"beyond":[36],"simple":[37],"actions":[39],"unify":[41],"it":[42],"with":[43],"learning.":[46],"Specifically,":[47],"develop":[49],"order-equivariant":[50,82,97],"neural":[51,62,108,132,142,165,175],"networks":[52,63,133,143],"(OENN),":[53],"which":[54,99,167],"generalize":[55],"standard":[56],"graph":[57,115,131],"message":[58],"passing":[59],"sheaf":[61,107,117,141],"via":[64,156],"the":[65,112,127,147,157,169],"theory":[66],"of":[67,173,192,196],"equivariant":[68,174],"vector":[69],"bundles":[70],"over":[71],"face":[72,75],"posets":[73],"(or":[74],"categories).":[76],"We":[77,110],"(i)":[78],"characterize":[79],"all":[80],"linear":[81],"maps,":[83,98],"(ii)":[84],"build":[85],"OENN":[86,152],"layers,":[87],"(iii)":[89],"prove":[90],"universal":[91],"approximation":[92],"theorems":[93],"(UATs)":[94],"for":[95,130],"continuous":[96],"are":[100],"new":[101],"results":[102,120],"even":[103],"when":[104],"restricted":[105],"to":[106,134,162,179,194],"networks.":[109],"illustrate":[111],"framework":[113],"on":[114],"models.":[118],"Our":[119],"can":[121,153],"also":[122],"be":[123,154],"seen":[124],"as":[125,144],"extending":[126,186],"known":[128],"UAT":[129],"a":[135],"more":[136],"general":[137,171],"setting":[138],"that":[139,151],"subsumes":[140],"well.":[145],"appendix,":[148],"show":[150],"connected,":[155],"action":[158],"groupoid":[159],"Grothendieck":[160],"construction,":[161],"CENN":[163],"(category-equivariant":[164],"network),":[166],"gives":[168],"categorical":[170,181],"form":[172],"networks,":[176],"allowing":[177],"us":[178],"leverage":[180],"symmetry":[182],"data":[184],"from":[190],"groups":[191],"symmetries":[193],"categories":[195],"transformations.":[197]},"counts_by_year":[],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2026-07-08T00:00:00"}