{"id":"https://openalex.org/W3034560159","doi":"https://doi.org/10.24963/ijcai.2020/341","title":"AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search","display_name":"AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034560159","doi":"https://doi.org/10.24963/ijcai.2020/341","mag":"3034560159"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/341","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/341","pdf_url":"https://www.ijcai.org/proceedings/2020/0341.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0341.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090695897","display_name":"Daoyuan Chen","orcid":"https://orcid.org/0000-0002-8015-2121"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daoyuan Chen","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046576694","display_name":"Yaliang Li","orcid":"https://orcid.org/0000-0002-4204-6096"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaliang Li","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101851065","display_name":"Minghui Qiu","orcid":"https://orcid.org/0000-0002-5184-9886"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minghui Qiu","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422377","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-8182-2852"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080243049","display_name":"Bofang Li","orcid":"https://orcid.org/0009-0000-9723-2999"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bofang Li","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040297543","display_name":"Bolin Ding","orcid":"https://orcid.org/0000-0003-1535-9692"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bolin Ding","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101786215","display_name":"Hongbo Deng","orcid":"https://orcid.org/0000-0002-9659-5111"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongbo Deng","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054621636","display_name":"Jun Huang","orcid":"https://orcid.org/0000-0002-7706-7081"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Huang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636012","display_name":"Wei Lin","orcid":"https://orcid.org/0000-0002-3003-0150"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Lin","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057864403","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-4220-2634"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingren Zhou","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2463","last_page":"2469"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.991100013256073,"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/computer-science","display_name":"Computer science","score":0.8588478565216064},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7008939981460571},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5603776574134827},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49472782015800476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4814716875553131},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.455584853887558},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.44121870398521423},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.44109222292900085},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.4380282163619995},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43397045135498047},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36390358209609985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8588478565216064},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7008939981460571},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5603776574134827},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49472782015800476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4814716875553131},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.455584853887558},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.44121870398521423},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.44109222292900085},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.4380282163619995},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43397045135498047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36390358209609985},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/341","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/341","pdf_url":"https://www.ijcai.org/proceedings/2020/0341.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/341","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/341","pdf_url":"https://www.ijcai.org/proceedings/2020/0341.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034560159.pdf","grobid_xml":"https://content.openalex.org/works/W3034560159.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2242818861","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2553303224","https://openalex.org/W2792764867","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2924902521","https://openalex.org/W2946417913","https://openalex.org/W2951104886","https://openalex.org/W2952902402","https://openalex.org/W2962739339","https://openalex.org/W2962847160","https://openalex.org/W2964303116","https://openalex.org/W2964347512","https://openalex.org/W2965373594","https://openalex.org/W2967733054","https://openalex.org/W2972324944","https://openalex.org/W2978017171","https://openalex.org/W2996428491","https://openalex.org/W2998183051","https://openalex.org/W3104216863","https://openalex.org/W3105966348","https://openalex.org/W3177265267","https://openalex.org/W4288102732","https://openalex.org/W4288256350","https://openalex.org/W4300687381"],"related_works":["https://openalex.org/W1512321724","https://openalex.org/W4231317009","https://openalex.org/W2367696392","https://openalex.org/W4383723869","https://openalex.org/W4293703255","https://openalex.org/W2161302774","https://openalex.org/W2388481516","https://openalex.org/W4384298135","https://openalex.org/W4383722264","https://openalex.org/W1723410974"],"abstract_inverted_index":{"Large":[0],"pre-trained":[1],"language":[2,14],"models":[3,44,90,140],"such":[4,46],"as":[5,109],"BERT":[6,41,54,68,86,123,147],"have":[7],"shown":[8],"their":[9],"effectiveness":[10,120],"in":[11,28,148,156],"various":[12],"natural":[13],"processing":[15],"tasks.":[16,59,93],"However,":[17],"the":[18,51,62,133],"huge":[19],"parameter":[20,159],"size":[21],"makes":[22],"them":[23],"difficult":[24],"to":[25,83,101,143,153],"be":[26],"deployed":[27],"real-time":[29],"applications":[30],"that":[31,77,136],"require":[32],"quick":[33],"inference":[34,149],"with":[35],"limited":[36],"resources.":[37],"Existing":[38],"methods":[39],"compress":[40,85],"into":[42,87],"small":[43,89],"while":[45,161],"compression":[47,74],"is":[48,164],"task-independent,":[49],"i.e.,":[50],"same":[52],"compressed":[53,139],"for":[55,91,121],"all":[56],"different":[57],"downstream":[58],"Motivated":[60],"by":[61],"necessity":[63],"and":[64,105,119,132,151],"benefits":[65],"of":[66,158],"task-oriented":[67,97],"compression,":[69],"we":[70],"propose":[71],"a":[72,96,114],"novel":[73],"method,":[75],"AdaBERT,":[76],"leverages":[78],"differentiable":[79],"Neural":[80],"Architecture":[81],"Search":[82],"automatically":[84],"task-adaptive":[88,122,138],"specific":[92],"We":[94,125],"incorporate":[95],"knowledge":[98],"distillation":[99],"loss":[100,108],"provide":[102],"search":[103,110],"hints":[104],"an":[106],"efficiency-aware":[107],"constraints,":[111],"which":[112],"enables":[113],"good":[115],"trade-off":[116],"between":[117],"efficiency":[118],"compression.":[124],"evaluate":[126],"AdaBERT":[127],"on":[128],"several":[129],"NLP":[130],"tasks,":[131],"results":[134],"demonstrate":[135],"those":[137],"are":[141],"12.7x":[142],"29.3x":[144],"faster":[145],"than":[146],"time":[150],"11.5x":[152],"17.0x":[154],"smaller":[155],"terms":[157],"size,":[160],"comparable":[162],"performance":[163],"maintained.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}