{"id":"https://openalex.org/W4394769152","doi":"https://doi.org/10.1145/3597503.3639216","title":"Learning in the Wild: Towards Leveraging Unlabeled Data for Effectively Tuning Pre-trained Code Models","display_name":"Learning in the Wild: Towards Leveraging Unlabeled Data for Effectively Tuning Pre-trained Code Models","publication_year":2024,"publication_date":"2024-04-12","ids":{"openalex":"https://openalex.org/W4394769152","doi":"https://doi.org/10.1145/3597503.3639216"},"language":"en","primary_location":{"id":"doi:10.1145/3597503.3639216","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597503.3639216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","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/A5012760348","display_name":"Shuzheng Gao","orcid":"https://orcid.org/0000-0002-8102-480X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Shuzheng Gao","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102961141","display_name":"Wenxin Mao","orcid":"https://orcid.org/0000-0001-6901-4433"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Mao","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061699251","display_name":"Cuiyun Gao","orcid":"https://orcid.org/0000-0003-4774-2434"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cuiyun Gao","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407830","display_name":"Li Li","orcid":"https://orcid.org/0000-0003-2990-1614"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047688641","display_name":"Xing Hu","orcid":"https://orcid.org/0000-0003-0093-3292"},"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":"Xing Hu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006669765","display_name":"Xin Xia","orcid":"https://orcid.org/0000-0002-6302-3256"},"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":"Xin Xia","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069596903","display_name":"Michael R. Lyu","orcid":"https://orcid.org/0000-0002-3666-5798"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Michael R. Lyu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5012760348"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":4.8652,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.9549958,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","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/T12535","display_name":"Machine Learning and Data Classification","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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10260","display_name":"Software Engineering Research","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/leverage","display_name":"Leverage (statistics)","score":0.8404806852340698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8250895738601685},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.8094905018806458},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.67195063829422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6344477534294128},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6184418201446533},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.47271794080734253},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46134382486343384},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.46095138788223267},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44738391041755676},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33962440490722656},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11812484264373779}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8404806852340698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250895738601685},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.8094905018806458},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.67195063829422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6344477534294128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6184418201446533},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.47271794080734253},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46134382486343384},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.46095138788223267},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44738391041755676},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33962440490722656},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11812484264373779},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3597503.3639216","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597503.3639216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3616843134","display_name":null,"funder_award_id":"2023A1515011959","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1560747311","https://openalex.org/W1956340063","https://openalex.org/W1983989471","https://openalex.org/W1993553653","https://openalex.org/W2072812688","https://openalex.org/W2123838014","https://openalex.org/W2138756793","https://openalex.org/W2516621648","https://openalex.org/W2963617989","https://openalex.org/W2988966271","https://openalex.org/W3005628256","https://openalex.org/W3034689979","https://openalex.org/W3086449553","https://openalex.org/W3091588759","https://openalex.org/W3105903381","https://openalex.org/W3159616622","https://openalex.org/W3161997752","https://openalex.org/W3174481817","https://openalex.org/W3177116043","https://openalex.org/W3177492177","https://openalex.org/W3194346579","https://openalex.org/W3197770791","https://openalex.org/W3198659451","https://openalex.org/W3204846429","https://openalex.org/W4205371973","https://openalex.org/W4213009331","https://openalex.org/W4221166942","https://openalex.org/W4249122235","https://openalex.org/W4284681867","https://openalex.org/W4284696121","https://openalex.org/W4284704125","https://openalex.org/W4285490394","https://openalex.org/W4285601373","https://openalex.org/W4298335024","https://openalex.org/W4308641647","https://openalex.org/W4313563640","https://openalex.org/W4384302749","https://openalex.org/W4388505012"],"related_works":["https://openalex.org/W2129767422","https://openalex.org/W3210196349","https://openalex.org/W4214728004","https://openalex.org/W2950181282","https://openalex.org/W2963261224","https://openalex.org/W2798287483","https://openalex.org/W2913410650","https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4308757581"],"abstract_inverted_index":{"Pre-trained":[0],"code":[1,10,58,94],"models":[2,14,59,95],"have":[3],"recently":[4],"achieved":[5],"substantial":[6],"improvements":[7],"in":[8,22,35,45,60,76],"many":[9],"intelligence":[11],"tasks.":[12,37,62],"These":[13],"are":[15,42],"first":[16],"pre-trained":[17,57,93],"on":[18,32],"large-scale":[19,73],"unlabeled":[20,74,87],"datasets":[21,34,41],"a":[23,108,129],"task-agnostic":[24],"manner":[25],"using":[26],"self-supervised":[27],"learning,":[28],"and":[29,89],"then":[30],"fine-tuned":[31],"labeled":[33,40],"downstream":[36],"However,":[38,100],"the":[39,54,72,77,92,97,103,124],"usually":[43],"limited":[44],"size":[46],"(i.e.,":[47],"human":[48],"intensive":[49],"efforts),":[50],"which":[51],"may":[52],"hinder":[53],"performance":[55],"of":[56,111],"specific":[61],"To":[63],"mitigate":[64],"this,":[65],"one":[66],"possible":[67],"solution":[68],"is":[69,128],"to":[70,117,121],"leverage":[71,123],"data":[75,88,105,127],"tuning":[78],"stage":[79],"by":[80],"pseudo-labeling,":[81],"i.e.,":[82,113],"generating":[83],"pseudo":[84],"labels":[85],"for":[86],"further":[90],"training":[91],"with":[96],"pseudo-labeled":[98,104,126],"data.":[99],"directly":[101],"employing":[102],"can":[106],"bring":[107],"large":[109],"amount":[110],"noise,":[112],"incorrect":[114],"labels,":[115],"leading":[116],"suboptimal":[118],"performance.":[119],"How":[120],"effectively":[122],"noisy":[125],"challenging":[130],"yet":[131],"under-explored":[132],"problem.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2024-04-13T00:00:00"}