{"id":"https://openalex.org/W3207879461","doi":null,"title":"Learning Equivariances and Partial Equivariances from Data","display_name":"Learning Equivariances and Partial Equivariances from Data","publication_year":2021,"publication_date":"2021-10-19","ids":{"openalex":"https://openalex.org/W3207879461","mag":"3207879461"},"language":"en","primary_location":{"id":"mag:3207879461","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2110.10211.pdf","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2110.10211.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084474296","display_name":"David W. Romero","orcid":"https://orcid.org/0000-0001-5446-1070","observed_orcids":["https://orcid.org/0000-0001-5446-1070"]},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"David W. Romero","raw_affiliation_strings":["vrije universiteit amsterdam"],"raw_orcid":"https://orcid.org/0000-0001-5446-1070","affiliations":[{"raw_affiliation_string":"vrije universiteit amsterdam","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056968977","display_name":"Suhas Lohit","orcid":"https://orcid.org/0000-0002-0392-3818","observed_orcids":["https://orcid.org/0000-0002-0392-3818"]},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]},{"id":"https://openalex.org/I4405253225","display_name":"Mitsubishi Electric Research Laboratories (United States)","ror":"https://ror.org/00e2e3n51","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4405253225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suhas Lohit","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories,#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-0392-3818","affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories,#TAB#","institution_ids":["https://openalex.org/I4210159266","https://openalex.org/I4405253225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.711899995803833,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.711899995803833,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11819999665021896,"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/T10320","display_name":"Neural Networks and Applications","score":0.021900000050663948,"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/rotation-equivariance","display_name":"rotation equivariance","score":0.4959999918937683},{"id":"https://openalex.org/keywords/discrete-groups","display_name":"discrete groups","score":0.43700000643730164},{"id":"https://openalex.org/keywords/continuous-groups","display_name":"continuous groups","score":0.9879999756813049},{"id":"https://openalex.org/keywords/natural-image-classification","display_name":"natural image classification","score":0.9150000214576721}],"concepts":[{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.9021413922309875},{"id":"https://openalex.org/C96469262","wikidata":"https://www.wikidata.org/wiki/Q1324364","display_name":"Homogeneous space","level":2,"score":0.7851296663284302},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6566539406776428},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6370744705200195},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5819131731987},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.5786795616149902},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47436341643333435},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4608565866947174},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46085020899772644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41833510994911194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4173876643180847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3749294877052307},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.36560067534446716},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3367081880569458},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22609740495681763},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16248008608818054},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.14850234985351562},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.14540544152259827},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3207879461","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2110.10211.pdf","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3207879461","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2110.10211.pdf","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1994197834","https://openalex.org/W2112796928","https://openalex.org/W2259303769","https://openalex.org/W2279221249","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2576915720","https://openalex.org/W2726670313","https://openalex.org/W2769152880","https://openalex.org/W2806857275","https://openalex.org/W2825179178","https://openalex.org/W2886272201","https://openalex.org/W2902266594","https://openalex.org/W2947599954","https://openalex.org/W2951004968","https://openalex.org/W2952860575","https://openalex.org/W2970774025","https://openalex.org/W2995360807","https://openalex.org/W3033455198","https://openalex.org/W3034504596","https://openalex.org/W3035684957","https://openalex.org/W3035702705","https://openalex.org/W3036272921","https://openalex.org/W3036737467","https://openalex.org/W3089607359","https://openalex.org/W3099892382","https://openalex.org/W3103313582","https://openalex.org/W3117555893","https://openalex.org/W3118608800","https://openalex.org/W3122369936","https://openalex.org/W3128694157","https://openalex.org/W3128876955","https://openalex.org/W3156762592","https://openalex.org/W3169316583","https://openalex.org/W3169403647"],"related_works":["https://openalex.org/W7133207135","https://openalex.org/W4400434628","https://openalex.org/W2951651290","https://openalex.org/W2279221249","https://openalex.org/W7006615242","https://openalex.org/W4390190268","https://openalex.org/W3168407340","https://openalex.org/W4312526534","https://openalex.org/W3129096215","https://openalex.org/W7133203806"],"abstract_inverted_index":{"Group":[0],"equivariant":[1,34,133],"Convolutional":[2],"Neural":[3],"Networks":[4],"(G-CNNs)":[5],"constrain":[6],"features":[7],"to":[8,15,37,84,108,136,162,196],"respect":[9],"the":[10,23,27,45,48,62,86,109,114],"chosen":[11,28],"symmetries,":[12],"and":[13,41,95,104,139,188,201],"lead":[14,36],"better":[16,52,82],"generalization":[17],"when":[18,183],"these":[19],"symmetries":[20,29,90],"appear":[21],"in":[22,69,101],"data.":[24,87],"However,":[25],"if":[26],"are":[30,160],"not":[31],"present,":[32],"group":[33,59,63],"architectures":[35],"overly":[38],"constrained":[39],"models":[40],"worse":[42],"performance.":[43],"Frequently,":[44],"distribution":[46],"of":[47,57,117,132],"data":[49,143],"can":[50],"be":[51],"represented":[53],"by":[54,61],"a":[55,58,65,75,102,112,130],"subset":[56],"than":[60],"as":[64],"whole,":[66],"e.g.,":[67,98,155,169],"rotations":[68],"$[-90^{\\circ},":[70],"90^{\\circ}]$.":[71],"In":[72,123],"such":[73],"cases,":[74],"model":[76],"that":[77],"respects":[78],"equivariance":[79,118,152,185],"partially":[80],"is":[81,186,194],"suited":[83],"represent":[85],"Moreover,":[88],"relevant":[89],"may":[91,119],"differ":[92,120],"for":[93,156,170],"low":[94],"high-level":[96],"features,":[97],"edge":[99],"orientations":[100],"face,":[103],"face":[105],"poses":[106],"relative":[107],"camera.":[110],"As":[111],"result,":[113],"optimal":[115],"level":[116],"per":[121],"layer.":[122],"this":[124],"work,":[125],"we":[126],"introduce":[127],"Partial":[128,148,176],"G-CNNs:":[129],"family":[131],"networks":[134],"able":[135,161],"learn":[137],"partial":[138],"full":[140,151,184],"equivariances":[141],"from":[142],"at":[144],"every":[145],"layer":[146],"end-to-end.":[147],"G-CNNs":[149,177,182],"retain":[150],"whenever":[153,165],"beneficial,":[154],"rotated":[157],"MNIST,":[158],"but":[159],"restrict":[163],"it":[164,166],"becomes":[167],"harmful,":[168],"6~/~9":[171],"or":[172],"natural":[173],"image":[174],"classification.":[175],"perform":[178],"on":[179],"par":[180],"with":[181],"necessary,":[187],"outperform":[189],"them":[190],"otherwise.":[191],"Our":[192],"method":[193],"applicable":[195],"discrete":[197],"groups,":[198],"continuous":[199],"groups":[200],"combinations":[202],"thereof.":[203]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-10-25T00:00:00"}