{"id":"https://openalex.org/W3215795311","doi":"https://doi.org/10.1038/s42256-023-00647-z","title":"Structure-inducing pre-training","display_name":"Structure-inducing pre-training","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W3215795311","doi":"https://doi.org/10.1038/s42256-023-00647-z","mag":"3215795311"},"language":"en","primary_location":{"id":"doi:10.1038/s42256-023-00647-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-023-00647-z","pdf_url":"https://www.nature.com/articles/s42256-023-00647-z.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.nature.com/articles/s42256-023-00647-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083993242","display_name":"Matthew B. A. McDermott","orcid":"https://orcid.org/0000-0001-6048-9707"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew B. A. McDermott","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6048-9707","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070234463","display_name":"Brendan Yap","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brendan Yap","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006650843","display_name":"Peter Szolovits","orcid":"https://orcid.org/0000-0001-8411-6403"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Szolovits","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8411-6403","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086052373","display_name":"Marinka \u017ditnik","orcid":"https://orcid.org/0000-0001-8530-7228"},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I107606265"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Marinka Zitnik","raw_affiliation_strings":["Broad Institute of MIT and Harvard, Cambridge, MA, USA","Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA","Harvard Data Science Initiative, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8530-7228","affiliations":[{"raw_affiliation_string":"Broad Institute of MIT and Harvard, Cambridge, MA, USA","institution_ids":["https://openalex.org/I107606265"]},{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard Data Science Initiative, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086052373"],"corresponding_institution_ids":["https://openalex.org/I107606265","https://openalex.org/I136199984","https://openalex.org/I2801851002"],"apc_list":{"value":11690,"currency":"USD","value_usd":11690},"apc_paid":{"value":11690,"currency":"USD","value_usd":11690},"fwci":2.8185,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91367668,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":"6","first_page":"612","last_page":"621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9950000047683716,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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/computer-science","display_name":"Computer science","score":0.7304378747940063},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6497288346290588},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6480847597122192},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5341813564300537},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.45340508222579956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44130006432533264},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42017924785614014},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4127345085144043},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38664427399635315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304378747940063},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6497288346290588},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6480847597122192},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5341813564300537},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.45340508222579956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44130006432533264},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42017924785614014},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4127345085144043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38664427399635315},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s42256-023-00647-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-023-00647-z","pdf_url":"https://www.nature.com/articles/s42256-023-00647-z.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1038/s42256-023-00647-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-023-00647-z","pdf_url":"https://www.nature.com/articles/s42256-023-00647-z.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4694536500","display_name":null,"funder_award_id":"FA8702-15-D-0001","funder_id":"https://openalex.org/F4320309369","funder_display_name":"Massachusetts Institute of Technology"},{"id":"https://openalex.org/G4950536974","display_name":null,"funder_award_id":"-0001","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5174054272","display_name":null,"funder_award_id":"FA8702-15-D-0001","funder_id":"https://openalex.org/F4320332467","funder_display_name":"U.S. Air Force"},{"id":"https://openalex.org/G6856159117","display_name":null,"funder_award_id":"Contract No. FA8702-15-D-0001","funder_id":"https://openalex.org/F4320332467","funder_display_name":"U.S. Air Force"},{"id":"https://openalex.org/G8645043690","display_name":null,"funder_award_id":"LM013337","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G865730642","display_name":null,"funder_award_id":"Air Force Contract No. FA8702-15-D-0001","funder_id":"https://openalex.org/F4320332467","funder_display_name":"U.S. Air Force"}],"funders":[{"id":"https://openalex.org/F4320307770","display_name":"AstraZeneca","ror":"https://ror.org/04r9x1a08"},{"id":"https://openalex.org/F4320309369","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"},{"id":"https://openalex.org/F4320334227","display_name":"Harvard Data Science Initiative, Harvard University","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3215795311.pdf"},"referenced_works_count":111,"referenced_works":["https://openalex.org/W2084809122","https://openalex.org/W2101234009","https://openalex.org/W2108598243","https://openalex.org/W2113459411","https://openalex.org/W2115062943","https://openalex.org/W2138621090","https://openalex.org/W2170682041","https://openalex.org/W2283196293","https://openalex.org/W2379594833","https://openalex.org/W2462700209","https://openalex.org/W2585247128","https://openalex.org/W2735621019","https://openalex.org/W2787560479","https://openalex.org/W2788730644","https://openalex.org/W2808000122","https://openalex.org/W2808556605","https://openalex.org/W2889498145","https://openalex.org/W2909137510","https://openalex.org/W2913820882","https://openalex.org/W2938830017","https://openalex.org/W2946417913","https://openalex.org/W2947423323","https://openalex.org/W2950374603","https://openalex.org/W2950411297","https://openalex.org/W2951433247","https://openalex.org/W2951585248","https://openalex.org/W2951599627","https://openalex.org/W2953356739","https://openalex.org/W2962767366","https://openalex.org/W2962815673","https://openalex.org/W2963341956","https://openalex.org/W2963854351","https://openalex.org/W2964015378","https://openalex.org/W2964231757","https://openalex.org/W2964271799","https://openalex.org/W2965373594","https://openalex.org/W2970641574","https://openalex.org/W2970727289","https://openalex.org/W2970771982","https://openalex.org/W2970986510","https://openalex.org/W2972167903","https://openalex.org/W2972498877","https://openalex.org/W2973114758","https://openalex.org/W2975059944","https://openalex.org/W2980360762","https://openalex.org/W2993670251","https://openalex.org/W2994967700","https://openalex.org/W2994968268","https://openalex.org/W2996035354","https://openalex.org/W2996428491","https://openalex.org/W2996604169","https://openalex.org/W2997200074","https://openalex.org/W2998385486","https://openalex.org/W3005441132","https://openalex.org/W3021975806","https://openalex.org/W3030163527","https://openalex.org/W3030978062","https://openalex.org/W3034238904","https://openalex.org/W3034381049","https://openalex.org/W3036490401","https://openalex.org/W3040213512","https://openalex.org/W3043746161","https://openalex.org/W3046375318","https://openalex.org/W3046882683","https://openalex.org/W3082274269","https://openalex.org/W3088265803","https://openalex.org/W3090656107","https://openalex.org/W3094771832","https://openalex.org/W3098903006","https://openalex.org/W3100283070","https://openalex.org/W3100807776","https://openalex.org/W3102844651","https://openalex.org/W3103092523","https://openalex.org/W3104415840","https://openalex.org/W3104425534","https://openalex.org/W3105816068","https://openalex.org/W3111174583","https://openalex.org/W3113280695","https://openalex.org/W3114219454","https://openalex.org/W3114916066","https://openalex.org/W3115295967","https://openalex.org/W3122924117","https://openalex.org/W3126254362","https://openalex.org/W3131755153","https://openalex.org/W3131870090","https://openalex.org/W3136047647","https://openalex.org/W3136379721","https://openalex.org/W3146384714","https://openalex.org/W3146944767","https://openalex.org/W3151929433","https://openalex.org/W3156159270","https://openalex.org/W3157265962","https://openalex.org/W3157746834","https://openalex.org/W3166593409","https://openalex.org/W3171434230","https://openalex.org/W3173783447","https://openalex.org/W3175423875","https://openalex.org/W3182352988","https://openalex.org/W3182414949","https://openalex.org/W3197123494","https://openalex.org/W3197780238","https://openalex.org/W3199484478","https://openalex.org/W3202026069","https://openalex.org/W3205068155","https://openalex.org/W3205223424","https://openalex.org/W3205726118","https://openalex.org/W4221153690","https://openalex.org/W4284702754","https://openalex.org/W6772452955","https://openalex.org/W6778883912","https://openalex.org/W6791955017"],"related_works":["https://openalex.org/W4231704780","https://openalex.org/W2083794993","https://openalex.org/W352609212","https://openalex.org/W1511772879","https://openalex.org/W4200340037","https://openalex.org/W4379115841","https://openalex.org/W608917066","https://openalex.org/W2185469136","https://openalex.org/W4283652261","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Abstract":[0],"Language":[1],"model":[2,35],"pre-training":[3,21,36,51,65,83,111,149,171],"and":[4,117,139,150,159,173],"the":[5,23,69,74,95,133,136,144,167],"derived":[6],"general-purpose":[7],"methods":[8,52,66,84,172],"have":[9],"reshaped":[10],"machine":[11],"learning":[12],"research.":[13],"However,":[14],"there":[15],"remains":[16,89],"considerable":[17],"uncertainty":[18],"regarding":[19],"why":[20],"improves":[22],"performance":[24],"of":[25,40,77,82,97,101,120,132,148,169,181],"downstream":[26],"tasks.":[27],"This":[28],"challenge":[29],"is":[30],"pronounced":[31],"when":[32],"using":[33],"language":[34],"in":[37,56],"domains":[38],"outside":[39],"natural":[41],"language.":[42],"Here":[43],"we":[44,108],"investigate":[45],"this":[46,87,99,106],"problem":[47],"by":[48],"analysing":[49],"how":[50,121],"impose":[53,67],"relational":[54,122,145],"structure":[55,123],"induced":[57,102],"per-sample":[58],"latent":[59],"spaces\u2014that":[60],"is,":[61],"what":[62],"constraints":[63],"do":[64],"on":[68,105],"distance":[70],"or":[71],"geometry":[72],"between":[73,143],"pre-trained":[75],"embeddings":[76],"samples.":[78],"A":[79],"comprehensive":[80,118],"review":[81],"reveals":[85],"that":[86,113],"question":[88],"open,":[90],"despite":[91],"theoretical":[92,130,164],"analyses":[93],"showing":[94],"importance":[96],"understanding":[98,119],"form":[100],"structure.":[103],"Based":[104],"review,":[107],"introduce":[109],"a":[110,115,129,141,178],"framework":[112,134],"enables":[114],"granular":[116],"can":[124],"be":[125],"induced.":[126],"We":[127],"present":[128],"analysis":[131],"from":[135],"first":[137],"principles":[138],"establish":[140,174],"connection":[142],"inductive":[146],"bias":[147],"fine-tuning":[151,161],"performance.":[152],"Empirical":[153],"studies":[154],"spanning":[155],"three":[156],"data":[157],"modalities":[158],"ten":[160],"tasks":[162],"confirm":[163],"analyses,":[165],"inform":[166],"design":[168],"novel":[170],"consistent":[175],"improvements":[176],"over":[177],"compelling":[179],"suite":[180],"methods.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}