{"id":"https://openalex.org/W3210128071","doi":"https://doi.org/10.48550/arxiv.2110.11526","title":"Wide Neural Networks Forget Less Catastrophically","display_name":"Wide Neural Networks Forget Less Catastrophically","publication_year":2021,"publication_date":"2021-10-21","ids":{"openalex":"https://openalex.org/W3210128071","doi":"https://doi.org/10.48550/arxiv.2110.11526","mag":"3210128071"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2110.11526","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.11526","pdf_url":"https://arxiv.org/pdf/2110.11526","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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.11526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010129552","display_name":"Seyed Iman Mirzadeh","orcid":"https://orcid.org/0000-0003-1586-0700","observed_orcids":["https://orcid.org/0000-0003-1586-0700"]},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mirzadeh, Seyed Iman","raw_affiliation_strings":["Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038288567","display_name":"Arslan Chaudhry","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaudhry, Arslan","raw_affiliation_strings":["Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yin, Dong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yin, Dong","raw_affiliation_strings":["Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070231479","display_name":"Huiyi Hu","orcid":"https://orcid.org/0000-0002-4398-5167","observed_orcids":["https://orcid.org/0000-0002-4398-5167"]},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hu, Huiyi","raw_affiliation_strings":["Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043910056","display_name":"Razvan Pascanu","orcid":"https://orcid.org/0000-0002-5470-1238","observed_orcids":["https://orcid.org/0000-0002-5470-1238"]},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pascanu, Razvan","raw_affiliation_strings":["Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081258844","display_name":"Dilan G\u00f6r\u00fcr","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gorur, Dilan","raw_affiliation_strings":["Washington State University","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050499655","display_name":"Mehrdad Farajtabar","orcid":"https://orcid.org/0000-0002-5510-518X","observed_orcids":["https://orcid.org/0000-0002-5510-518X"]},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farajtabar, Mehrdad","raw_affiliation_strings":["Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":25,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9922000169754028,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9922000169754028,"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":0.0008999999845400453,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0003000000142492354,"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/catastrophic-forgetting","display_name":"catastrophic forgetting","score":0.9990000128746033},{"id":"https://openalex.org/keywords/continual-learning","display_name":"continual learning","score":0.9810000061988831},{"id":"https://openalex.org/keywords/learning-dynamics","display_name":"learning dynamics","score":0.6769999861717224},{"id":"https://openalex.org/keywords/sparsity","display_name":"sparsity","score":0.6510000228881836},{"id":"https://openalex.org/keywords/lazy-training","display_name":"lazy training","score":0.8259999752044678},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.7360000014305115}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.9645954370498657},{"id":"https://openalex.org/C47559304","wikidata":"https://www.wikidata.org/wiki/Q1702189","display_name":"Orthogonalization","level":2,"score":0.6943202614784241},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6690914630889893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6333378553390503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6058250069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4962514042854309},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4909253418445587},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4564897418022156},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14210152626037598},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.11664828658103943},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09210768342018127},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2110.11526","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.11526","pdf_url":"https://arxiv.org/pdf/2110.11526","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":null,"raw_type":"text"},{"id":"mag:3210128071","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2110.11526.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},{"id":"doi:10.48550/arxiv.2110.11526","doi":"https://doi.org/10.48550/arxiv.2110.11526","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.11526","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.11526","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.11526","pdf_url":"https://arxiv.org/pdf/2110.11526","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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3210128071.pdf","grobid_xml":"https://content.openalex.org/works/W3210128071.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1535804263","https://openalex.org/W1682403713","https://openalex.org/W1815076433","https://openalex.org/W2047057213","https://openalex.org/W2107878631","https://openalex.org/W2113839990","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2426267443","https://openalex.org/W2554616628","https://openalex.org/W2554863749","https://openalex.org/W2557283755","https://openalex.org/W2560647685","https://openalex.org/W2583761661","https://openalex.org/W2618767506","https://openalex.org/W2737492962","https://openalex.org/W2768412495","https://openalex.org/W2788388592","https://openalex.org/W2806984819","https://openalex.org/W2809090039","https://openalex.org/W2811024793","https://openalex.org/W2898290017","https://openalex.org/W2899063268","https://openalex.org/W2902456977","https://openalex.org/W2902625698","https://openalex.org/W2903996579","https://openalex.org/W2912322140","https://openalex.org/W2912515466","https://openalex.org/W2932484476","https://openalex.org/W2942052807","https://openalex.org/W2947461406","https://openalex.org/W2952204734","https://openalex.org/W2962698540","https://openalex.org/W2962724315","https://openalex.org/W2963393838","https://openalex.org/W2963444224","https://openalex.org/W2963577698","https://openalex.org/W2964137095","https://openalex.org/W2964790801","https://openalex.org/W2970330753","https://openalex.org/W2970505118","https://openalex.org/W2980753060","https://openalex.org/W2981407587","https://openalex.org/W3000677656","https://openalex.org/W3001279689","https://openalex.org/W3030163527","https://openalex.org/W3037853434","https://openalex.org/W3040607201","https://openalex.org/W3090618925","https://openalex.org/W3092475441","https://openalex.org/W3094105627","https://openalex.org/W3098195673","https://openalex.org/W3103936143","https://openalex.org/W3122207284","https://openalex.org/W3126553126","https://openalex.org/W3132646476","https://openalex.org/W3157424867","https://openalex.org/W3170325272","https://openalex.org/W3209540659","https://openalex.org/W4319988532"],"related_works":["https://openalex.org/W4392735801","https://openalex.org/W4404521036","https://openalex.org/W4417539390","https://openalex.org/W4387322958","https://openalex.org/W2966137695","https://openalex.org/W2949038944","https://openalex.org/W7134038763","https://openalex.org/W4283385216","https://openalex.org/W7127616349","https://openalex.org/W4414742179"],"abstract_inverted_index":{"A":[0],"primary":[1],"focus":[2,68],"area":[3],"in":[4,14,33,64],"continual":[5,34,61,137],"learning":[6,35,62,105,138],"research":[7],"is":[8,37,51],"alleviating":[9],"the":[10,26,30,70,75,80,104,108,130],"\"catastrophic":[11],"forgetting\"":[12],"problem":[13],"neural":[15,45,81],"networks":[16,46],"by":[17],"designing":[18],"new":[19],"algorithms":[20],"that":[21,89,126],"are":[22,127],"more":[23],"robust":[24],"to":[25,48],"distribution":[27],"shifts.":[28],"While":[29],"recent":[31],"progress":[32],"literature":[36],"encouraging,":[38],"our":[39],"understanding":[40],"of":[41,44,58,77,79,107],"what":[42],"properties":[43],"contribute":[47],"catastrophic":[49,85],"forgetting":[50],"still":[52],"limited.":[53],"To":[54,98],"address":[55],"this,":[56],"instead":[57],"focusing":[59],"on":[60,69,84,96],"algorithms,":[63],"this":[65,100],"work,":[66],"we":[67,102],"model":[71],"itself":[72],"and":[73,87,118,136],"study":[74,103],"impact":[76],"\"width\"":[78],"network":[82,109],"architecture":[83],"forgetting,":[86],"show":[88],"width":[90],"has":[91],"a":[92],"surprisingly":[93],"significant":[94],"effect":[95],"forgetting.":[97],"explain":[99],"effect,":[101],"dynamics":[106],"from":[110],"various":[111],"perspectives":[112],"such":[113],"as":[114],"gradient":[115],"orthogonality,":[116],"sparsity,":[117],"lazy":[119],"training":[120],"regime.":[121],"We":[122],"provide":[123],"potential":[124],"explanations":[125],"consistent":[128],"with":[129],"empirical":[131],"results":[132],"across":[133],"different":[134],"architectures":[135],"benchmarks.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-11-08T00:00:00"}