{"id":"https://openalex.org/W4385484863","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191351","title":"GamMa: Efficient Fine-Tuning of Pre-Trained Language Models Using Gradient Activation Mapping Masking","display_name":"GamMa: Efficient Fine-Tuning of Pre-Trained Language Models Using Gradient Activation Mapping Masking","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385484863","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191351"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191351","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113128933","display_name":"Anchun Gui","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Anchun Gui","raw_affiliation_strings":["School of Informatics, Xiamen University,Xiamen,China","School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112972528","display_name":"Jinqiang Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiang Ye","raw_affiliation_strings":["School of Informatics, Xiamen University,Xiamen,China","School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101631160","display_name":"Han Xiao","orcid":"https://orcid.org/0000-0002-3548-3204"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Xiao","raw_affiliation_strings":["School of Informatics, Xiamen University,Xiamen,China","School of Informatics, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113128933"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08461373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"8"},"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":0.9955999851226807,"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":0.9782000184059143,"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":0.808424711227417},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7178748846054077},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6232682466506958},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5878423452377319},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.5424045920372009},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4681307077407837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4385804235935211},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43056023120880127},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.339305579662323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808424711227417},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7178748846054077},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6232682466506958},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5878423452377319},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.5424045920372009},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4681307077407837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4385804235935211},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43056023120880127},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.339305579662323},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191351","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5520567748","display_name":null,"funder_award_id":"62006201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2295107390","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2950784811","https://openalex.org/W2962858109","https://openalex.org/W2964303116","https://openalex.org/W2964303773","https://openalex.org/W2965373594","https://openalex.org/W2970120757","https://openalex.org/W2975185270","https://openalex.org/W2977944219","https://openalex.org/W2979826702","https://openalex.org/W3020268419","https://openalex.org/W3023285645","https://openalex.org/W3034999214","https://openalex.org/W3168867926","https://openalex.org/W3173787059","https://openalex.org/W3174702398","https://openalex.org/W3174770825","https://openalex.org/W3175604467","https://openalex.org/W3176828726","https://openalex.org/W3199761064","https://openalex.org/W3205949070","https://openalex.org/W3206907172","https://openalex.org/W4205991051","https://openalex.org/W4221145545","https://openalex.org/W4225410153","https://openalex.org/W4287122891","https://openalex.org/W4288026527","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4322588812","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6758026734","https://openalex.org/W6759579507","https://openalex.org/W6768061436","https://openalex.org/W6768586863","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6796710205","https://openalex.org/W6802744804"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W3023285645","https://openalex.org/W3037551068","https://openalex.org/W3023594376","https://openalex.org/W4287802662","https://openalex.org/W4309877123"],"abstract_inverted_index":{"Recently":[0],"pre-trained":[1,70],"language":[2,10],"models":[3,16],"have":[4],"shown":[5],"great":[6],"success":[7],"in":[8],"natural":[9],"processing.":[11],"To":[12,56],"fully":[13],"leverage":[14],"these":[15,58,115],"on":[17,151],"downstream":[18],"tasks,":[19],"full":[20],"fine-tuning":[21,112],"has":[22,53],"become":[23],"a":[24,46,62],"ubiquitous":[25],"training":[26,145],"paradigm.":[27],"However,":[28],"it":[29,43,131],"is":[30],"inefficient":[31],"and":[32,92],"resource-intensive":[33],"to":[34,67,96],"fine-tune":[35,68],"the":[36,40,69,82,86,99,106,111,127,136,152,160],"entire":[37],"parameters":[38,50,84,101,117,143],"of":[39,49,88],"model":[41,107,138],"since":[42],"always":[44],"employs":[45],"huge":[47],"scale":[48],"(e.g.,":[51],"GPT-3":[52],"175B":[54],"parameters).":[55],"address":[57],"issues,":[59],"we":[60],"propose":[61],"simple":[63],"yet":[64],"effective":[65],"method":[66,158],"models,":[71],"named":[72],"Gradient":[73],"activation":[74,90],"mapping":[75],"Masking":[76],"(GamMa).":[77],"Specifically,":[78],"GamMa":[79,122],"first":[80],"detects":[81],"class-specific":[83],"from":[85],"perspective":[87],"gradient":[89],"mapping,":[91],"then":[93],"aggregates":[94],"them":[95],"work":[97],"out":[98],"particular":[100],"that":[102,156],"can":[103],"greatly":[104],"influence":[105],"predictive":[108],"boundaries.":[109],"During":[110],"process,":[113],"only":[114],"significant":[116],"are":[118,147],"updated":[119],"necessarily.":[120],"Besides,":[121],"takes":[123],"several":[124],"advantages":[125],"over":[126],"previous":[128],"approaches:":[129],"(i)":[130],"does":[132],"not":[133],"require":[134],"modifying":[135],"original":[137],"structure;":[139],"(ii)":[140],"neither":[141],"extra":[142],"nor":[144],"budgets":[146],"introduced.":[148],"Extensive":[149],"experiments":[150],"GLUE":[153],"benchmark":[154],"demonstrate":[155],"our":[157],"outperforms":[159],"current":[161],"state-of-the-art":[162],"counterparts.":[163]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}