{"id":"https://openalex.org/W4389519452","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.75","title":"Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization","display_name":"Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389519452","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.75"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.75","pdf_url":"https://aclanthology.org/2023.findings-emnlp.75.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.findings-emnlp.75.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033407215","display_name":"Kaihang Pan","orcid":"https://orcid.org/0009-0001-2967-4573"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["CN","KY"],"is_corresponding":false,"raw_author_name":"Kaihang Pan","raw_affiliation_strings":["DAMO Academy, Alibaba Group,","Zhejiang University,"],"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group,","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Zhejiang University,","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Zhejiang University,"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101058544","display_name":"Hongye Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Hongye Song","raw_affiliation_strings":["DAMO Academy, Alibaba Group,"],"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group,","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748932","display_name":"Jun Lin","orcid":"https://orcid.org/0000-0002-5926-5391"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Jun Lin","raw_affiliation_strings":["DAMO Academy, Alibaba Group,"],"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group,","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101985030","display_name":"Xiaozhong Liu","orcid":"https://orcid.org/0000-0003-3477-8323"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaozhong Liu","raw_affiliation_strings":["Worcester Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063062444","display_name":"Siliang Tang","orcid":"https://orcid.org/0000-0002-7356-9711"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["Zhejiang University,"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063062444"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.5139,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72907578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1059","last_page":"1077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9945999979972839,"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":0.9926000237464905,"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/overfitting","display_name":"Overfitting","score":0.857272207736969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8161865472793579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7058210372924805},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6987164616584778},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.6519871950149536},{"id":"https://openalex.org/keywords/early-stopping","display_name":"Early stopping","score":0.6150166988372803},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6033403873443604},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5974195599555969},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5961838364601135},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5159516930580139},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4623052179813385},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.46080896258354187},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.43974569439888},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15580198168754578},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1090705394744873}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.857272207736969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8161865472793579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7058210372924805},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6987164616584778},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.6519871950149536},{"id":"https://openalex.org/C5465570","wikidata":"https://www.wikidata.org/wiki/Q5326898","display_name":"Early stopping","level":3,"score":0.6150166988372803},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6033403873443604},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5974195599555969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5961838364601135},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5159516930580139},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4623052179813385},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.46080896258354187},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.43974569439888},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15580198168754578},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1090705394744873},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.findings-emnlp.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.75","pdf_url":"https://aclanthology.org/2023.findings-emnlp.75.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.75","pdf_url":"https://aclanthology.org/2023.findings-emnlp.75.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":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1781607827","display_name":null,"funder_award_id":"62272411","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3551653136","display_name":null,"funder_award_id":"2018AAA0101900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5087339601","display_name":null,"funder_award_id":"01019","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322927","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389519452.pdf"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W2028175314","https://openalex.org/W2114524997","https://openalex.org/W2137825550","https://openalex.org/W2160660844","https://openalex.org/W2163302275","https://openalex.org/W2163455955","https://openalex.org/W2170240176","https://openalex.org/W2251939518","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2625674597","https://openalex.org/W2753160622","https://openalex.org/W2765407302","https://openalex.org/W2787501667","https://openalex.org/W2803777992","https://openalex.org/W2923014074","https://openalex.org/W2943552823","https://openalex.org/W2956105246","https://openalex.org/W2963341924","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W2969897437","https://openalex.org/W2979826702","https://openalex.org/W3026404337","https://openalex.org/W3034549794","https://openalex.org/W3091905774","https://openalex.org/W3129831491","https://openalex.org/W3172642864","https://openalex.org/W3173777717","https://openalex.org/W3174770825","https://openalex.org/W3183719433","https://openalex.org/W3185341429","https://openalex.org/W3197876970","https://openalex.org/W3198377975","https://openalex.org/W3198571508","https://openalex.org/W3205717164","https://openalex.org/W4205991051","https://openalex.org/W4226129861","https://openalex.org/W4226198567","https://openalex.org/W4281862540","https://openalex.org/W4285069877","https://openalex.org/W4285107336","https://openalex.org/W4285247752","https://openalex.org/W4288089799","https://openalex.org/W4290058858","https://openalex.org/W4292779060","https://openalex.org/W4294646197","https://openalex.org/W4297165176","https://openalex.org/W4303633609","https://openalex.org/W4307079201","https://openalex.org/W4307653761","https://openalex.org/W4312245888","https://openalex.org/W4320536797","https://openalex.org/W4324321325","https://openalex.org/W4385573776","https://openalex.org/W4385714029","https://openalex.org/W4386081021","https://openalex.org/W4387390235"],"related_works":["https://openalex.org/W4254751698","https://openalex.org/W2922073769","https://openalex.org/W4320854463","https://openalex.org/W3040157805","https://openalex.org/W4288022214","https://openalex.org/W4283736627","https://openalex.org/W4387799548","https://openalex.org/W4385768004","https://openalex.org/W3008105014","https://openalex.org/W4308755723"],"abstract_inverted_index":{"Prompt":[0],"tuning":[1,23],"is":[2],"a":[3,34,84,102,110,125,134,159],"parameter-efficient":[4],"method,":[5],"which":[6],"learns":[7],"soft":[8,38,64],"prompts":[9,65],"and":[10,156],"conditions":[11],"frozen":[12],"language":[13],"models":[14],"to":[15,48,62,69,72,108,129],"perform":[16],"specific":[17],"downstream":[18,74,154],"tasks.":[19,75],"Though":[20],"effective,":[21],"prompt":[22,112],"under":[24],"few-shot":[25,49,94,153],"settings":[26],"on":[27,33],"the":[28,41,78,139],"one":[29],"hand":[30],"heavily":[31],"relies":[32],"good":[35],"initialization":[36,113],"of":[37,105,141],"prompts.":[39],"On":[40],"other":[42],"hand,":[43],"it":[44,122],"can":[45],"easily":[46],"overfit":[47],"training":[50],"samples,":[51],"thereby":[52],"undermining":[53],"generalizability.":[54],"Existing":[55],"works":[56],"leverage":[57],"pre-training":[58],"or":[59],"supervised":[60],"meta-learning":[61,100],"initialize":[63],"but":[66],"they":[67],"fail":[68],"data-efficiently":[70],"generalize":[71],"unseen":[73],"To":[76],"address":[77],"above":[79],"problems,":[80],"this":[81],"paper":[82],"proposes":[83],"novel":[85],"Self-sUpervised":[86],"meta-Prompt":[87],"learning":[88],"framework":[89],"with":[90,101],"MEta-gradient":[91],"Regularization":[92],"for":[93,114,151,166],"generalization":[95,162],"(SUPMER).":[96],"SUPMER":[97,147,167],"leverages":[98],"self-supervised":[99],"diverse":[103],"set":[104],"well-designed":[106],"meta-tasks":[107],"learn":[109],"universal":[111],"efficient":[115],"adaptation":[116],"using":[117],"only":[118],"unlabeled":[119],"data.":[120],"Additionally,":[121],"jointly":[123],"meta-learns":[124],"gradient":[126],"regularization":[127],"function":[128],"transform":[130],"raw":[131],"gradients":[132],"into":[133],"domain-generalizable":[135],"direction,":[136],"thus":[137],"alleviating":[138],"problem":[140],"overfitting.":[142],"Extensive":[143],"experiments":[144],"show":[145],"that":[146],"achieves":[148],"better":[149],"performance":[150],"different":[152],"tasks,":[155],"also":[157],"exhibits":[158],"stronger":[160],"domain":[161],"ability.":[163],"The":[164],"code":[165],"will":[168],"be":[169],"available":[170],"at":[171],"https://github.com/beepkh/SUPMER.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}