{"id":"https://openalex.org/W4318464561","doi":"https://doi.org/10.3390/s23031483","title":"LAD: Layer-Wise Adaptive Distillation for BERT Model Compression","display_name":"LAD: Layer-Wise Adaptive Distillation for BERT Model Compression","publication_year":2023,"publication_date":"2023-01-28","ids":{"openalex":"https://openalex.org/W4318464561","doi":"https://doi.org/10.3390/s23031483","pmid":"https://pubmed.ncbi.nlm.nih.gov/36772523"},"language":"en","primary_location":{"id":"doi:10.3390/s23031483","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23031483","pdf_url":"https://www.mdpi.com/1424-8220/23/3/1483/pdf?version=1675752966","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/3/1483/pdf?version=1675752966","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040237383","display_name":"Ying-Jia Lin","orcid":"https://orcid.org/0000-0003-4347-0232"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying-Jia Lin","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 70101, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-4347-0232","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 70101, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714455","display_name":"Kuan\u2010Yu Chen","orcid":"https://orcid.org/0000-0002-4020-9103"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Yu Chen","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 70101, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 70101, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101898313","display_name":"Hung\u2010Yu Kao","orcid":"https://orcid.org/0000-0002-8890-8544"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hung-Yu Kao","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 70101, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-8890-8544","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 70101, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101898313"],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":3.1478,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93064741,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"23","issue":"3","first_page":"1483","last_page":"1483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.995199978351593,"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":0.9789000153541565,"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/distillation","display_name":"Distillation","score":0.7621966600418091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733009934425354},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6432483196258545},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6342363357543945},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5498037338256836},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5407495498657227},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.45570996403694153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42956164479255676},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42752882838249207},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4092542231082916},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11312812566757202},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10885286331176758},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09710639715194702}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7621966600418091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733009934425354},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6432483196258545},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6342363357543945},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5498037338256836},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5407495498657227},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.45570996403694153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42956164479255676},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42752882838249207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4092542231082916},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11312812566757202},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10885286331176758},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09710639715194702},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/s23031483","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23031483","pdf_url":"https://www.mdpi.com/1424-8220/23/3/1483/pdf?version=1675752966","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:36772523","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36772523","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9921705","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9921705","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9921705/pdf/sensors-23-01483.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:915b77236cf5432bb0bbc93241109002","is_oa":true,"landing_page_url":"https://doaj.org/article/915b77236cf5432bb0bbc93241109002","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 3, p 1483 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/3/1483/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23031483","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 23; Issue 3; Pages: 1483","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23031483","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23031483","pdf_url":"https://www.mdpi.com/1424-8220/23/3/1483/pdf?version=1675752966","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[{"id":"https://openalex.org/G2057974104","display_name":null,"funder_award_id":"MOST 111-2221-E-006-001","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4318464561.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W2130158090","https://openalex.org/W2251939518","https://openalex.org/W2294370754","https://openalex.org/W2799054028","https://openalex.org/W2950621961","https://openalex.org/W2950813464","https://openalex.org/W2970597249","https://openalex.org/W2996035354","https://openalex.org/W3008374555","https://openalex.org/W3030163527","https://openalex.org/W3101248447","https://openalex.org/W3177378457","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6757817989","https://openalex.org/W6769627184"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W2768175398","https://openalex.org/W2344382886","https://openalex.org/W19111321","https://openalex.org/W2412887479","https://openalex.org/W2953684491","https://openalex.org/W2015158429","https://openalex.org/W2080290893","https://openalex.org/W2117216852","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"with":[2,64,103],"large-scale":[3],"pre-trained":[4,40],"language":[5,15,41],"models":[6,153],"(e.g.,":[7],"BERT)":[8],"have":[9,32],"brought":[10],"significant":[11],"potential":[12],"to":[13,37,44,60,90,109,119],"natural":[14],"processing.":[16],"However,":[17,43],"the":[18,39,46,68,92,116,120,147],"large":[19,52],"model":[20,63,70,93,118],"size":[21,94],"hinders":[22],"their":[23],"use":[24],"in":[25,50,107],"IoT":[26],"and":[27,149],"edge":[28],"devices.":[29],"Several":[30],"studies":[31],"utilized":[33],"task-specific":[34,83,156],"knowledge":[35,59,114,129],"distillation":[36,84,157],"compress":[38],"models.":[42],"reduce":[45,91],"number":[47],"of":[48,95],"layers":[49,66],"a":[51,54,61,82,133],"model,":[53,135],"sound":[55],"strategy":[56],"for":[57,132],"distilling":[58],"student":[62,121,134,152],"fewer":[65],"than":[67],"teacher":[69,117,139],"is":[71],"lacking.":[72],"In":[73],"this":[74],"work,":[75],"we":[76],"present":[77],"Layer-wise":[78],"Adaptive":[79],"Distillation":[80],"(LAD),":[81],"framework":[85],"that":[86,145],"can":[87],"be":[88],"used":[89],"BERT.":[96],"We":[97],"design":[98],"an":[99,127],"iterative":[100],"aggregation":[101],"mechanism":[102],"multiple":[104],"gate":[105],"blocks":[106],"LAD":[108,151],"adaptively":[110],"distill":[111],"layer-wise":[112],"internal":[113],"from":[115],"model.":[122],"The":[123,141],"proposed":[124],"method":[125],"enables":[126],"effective":[128],"transfer":[130],"process":[131],"without":[136],"skipping":[137],"any":[138],"layers.":[140],"experimental":[142],"results":[143],"show":[144],"both":[146],"six-layer":[148],"four-layer":[150],"outperform":[154],"previous":[155],"approaches":[158],"during":[159],"GLUE":[160],"tasks.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}