{"id":"https://openalex.org/W4401042569","doi":"https://doi.org/10.18653/v1/2024.naacl-long.345","title":"SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics","display_name":"SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401042569","doi":"https://doi.org/10.18653/v1/2024.naacl-long.345"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.naacl-long.345","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.naacl-long.345","pdf_url":"https://aclanthology.org/2024.naacl-long.345.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.naacl-long.345.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064497251","display_name":"Arash Ardakani","orcid":"https://orcid.org/0000-0003-3274-2394"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arash Ardakani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062687390","display_name":"Altan Haan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Altan Haan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102518307","display_name":"Shangyin Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shangyin Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019066795","display_name":"Doru Thom Popovici","orcid":"https://orcid.org/0000-0002-7271-8092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Doru Thom Popovici","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059427197","display_name":"Alvin Cheung","orcid":"https://orcid.org/0000-0001-6261-6263"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alvin Cheung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023233400","display_name":"Costin Iancu","orcid":"https://orcid.org/0000-0001-7845-2427"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Costin Iancu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101569699","display_name":"Koushik Sen","orcid":"https://orcid.org/0000-0002-4539-9188"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koushik Sen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2219,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.824911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6218","last_page":"6236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9366000294685364,"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/T10320","display_name":"Neural Networks and Applications","score":0.9366000294685364,"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":0.6958565711975098},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6648234128952026},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4626966118812561},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.41662928462028503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3314662277698517},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.16830945014953613},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1603851318359375},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12511587142944336},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07354700565338135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958565711975098},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6648234128952026},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4626966118812561},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.41662928462028503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3314662277698517},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.16830945014953613},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1603851318359375},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12511587142944336},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07354700565338135},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.naacl-long.345","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.naacl-long.345","pdf_url":"https://aclanthology.org/2024.naacl-long.345.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.naacl-long.345","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.naacl-long.345","pdf_url":"https://aclanthology.org/2024.naacl-long.345.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G1562478397","display_name":"III: Medium: Collaborative Research: Reasoning about Optimizers for Data-Intensive Systems","funder_award_id":"1955488","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2712957708","display_name":"CAREER: Generating Application-Specific Database Management Systems","funder_award_id":"2027575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2859789661","display_name":null,"funder_award_id":"N00014-21-1-2724","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5944197847","display_name":null,"funder_award_id":"W911NF2110339","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G5974677782","display_name":null,"funder_award_id":"DE-SC0016260","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401042569.pdf","grobid_xml":"https://content.openalex.org/works/W4401042569.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Arash":[0],"Ardakani,":[1],"Altan":[2],"Haan,":[3],"Shangyin":[4],"Tan,":[5],"Doru":[6],"Thom":[7],"Popovici,":[8],"Alvin":[9],"Cheung,":[10],"Costin":[11],"Iancu,":[12],"Koushik":[13],"Sen.":[14],"Proceedings":[15],"of":[16,20,25],"the":[17,21,26],"2024":[18],"Conference":[19],"North":[22],"American":[23],"Chapter":[24],"Association":[27],"for":[28],"Computational":[29],"Linguistics:":[30],"Human":[31],"Language":[32],"Technologies":[33],"(Volume":[34],"1:":[35],"Long":[36],"Papers).":[37],"2024.":[38]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}