{"id":"https://openalex.org/W4410552982","doi":"https://doi.org/10.1109/saner64311.2025.00065","title":"How to Select Pre-Trained Code Models for Reuse? A Learning Perspective","display_name":"How to Select Pre-Trained Code Models for Reuse? A Learning Perspective","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4410552982","doi":"https://doi.org/10.1109/saner64311.2025.00065"},"language":"en","primary_location":{"id":"doi:10.1109/saner64311.2025.00065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner64311.2025.00065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)","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/A5005288979","display_name":"Zhangqian Bi","orcid":"https://orcid.org/0000-0003-2257-9052"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhangqian Bi","raw_affiliation_strings":["Services Computing Technology and System Lab, Cluster and Grid Computing Lab,National Engineering Research Center for Big Data Technology and System,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Services Computing Technology and System Lab, Cluster and Grid Computing Lab,National Engineering Research Center for Big Data Technology and System,Wuhan,China","institution_ids":["https://openalex.org/I4210144487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101555948","display_name":"Yao Wan","orcid":"https://orcid.org/0000-0001-6937-4180"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Wan","raw_affiliation_strings":["Services Computing Technology and System Lab, Cluster and Grid Computing Lab,National Engineering Research Center for Big Data Technology and System,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Services Computing Technology and System Lab, Cluster and Grid Computing Lab,National Engineering Research Center for Big Data Technology and System,Wuhan,China","institution_ids":["https://openalex.org/I4210144487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104142389","display_name":"Zhaoyang Chu","orcid":"https://orcid.org/0000-0003-4333-8063"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyang Chu","raw_affiliation_strings":["Services Computing Technology and System Lab, Cluster and Grid Computing Lab,National Engineering Research Center for Big Data Technology and System,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Services Computing Technology and System Lab, Cluster and Grid Computing Lab,National Engineering Research Center for Big Data Technology and System,Wuhan,China","institution_ids":["https://openalex.org/I4210144487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108752470","display_name":"You Hu","orcid":"https://orcid.org/0009-0006-9823-1465"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Hu","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342745","display_name":"Junyi Zhang","orcid":"https://orcid.org/0000-0001-8986-6588"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyi Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412598","display_name":"Hongyu Zhang","orcid":"https://orcid.org/0000-0002-3063-9425"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Zhang","raw_affiliation_strings":["School of Big Data and Software Engineering, Chongqing University,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"School of Big Data and Software Engineering, Chongqing University,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051512158","display_name":"Guandong Xu","orcid":"https://orcid.org/0000-0003-4493-6663"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guandong Xu","raw_affiliation_strings":["School of Computer Science, University of Technology Sydney,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022262922","display_name":"Hai Jin","orcid":"https://orcid.org/0000-0002-3934-7605"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Jin","raw_affiliation_strings":["Services Computing Technology and System Lab, Cluster and Grid Computing Lab,National Engineering Research Center for Big Data Technology and System,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Services Computing Technology and System Lab, Cluster and Grid Computing Lab,National Engineering Research Center for Big Data Technology and System,Wuhan,China","institution_ids":["https://openalex.org/I4210144487"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5005288979"],"corresponding_institution_ids":["https://openalex.org/I4210144487"],"apc_list":null,"apc_paid":null,"fwci":2.8414,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90852218,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9524000287055969,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9524000287055969,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9178000092506409,"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/T12171","display_name":"Open Education and E-Learning","score":0.9053000211715698,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/perspective","display_name":"Perspective (graphical)","score":0.7332970499992371},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7255481481552124},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6606694459915161},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5323747992515564},{"id":"https://openalex.org/keywords/code-reuse","display_name":"Code reuse","score":0.521252453327179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40180447697639465},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3965318202972412},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3703170120716095},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14858046174049377},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.07978922128677368}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7332970499992371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7255481481552124},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6606694459915161},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5323747992515564},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.521252453327179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40180447697639465},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3965318202972412},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3703170120716095},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14858046174049377},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.07978922128677368},{"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/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/saner64311.2025.00065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saner64311.2025.00065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W2008056655","https://openalex.org/W2069870183","https://openalex.org/W2087920662","https://openalex.org/W2103260577","https://openalex.org/W2156598245","https://openalex.org/W2282866165","https://openalex.org/W2794601162","https://openalex.org/W2804935296","https://openalex.org/W2884276923","https://openalex.org/W2888557792","https://openalex.org/W2900670268","https://openalex.org/W2970677506","https://openalex.org/W2999343753","https://openalex.org/W3011632945","https://openalex.org/W3034999214","https://openalex.org/W3035272520","https://openalex.org/W3045279034","https://openalex.org/W3093475474","https://openalex.org/W3098605233","https://openalex.org/W3170092793","https://openalex.org/W3176687337","https://openalex.org/W3194668998","https://openalex.org/W3198685994","https://openalex.org/W4205712089","https://openalex.org/W4220722393","https://openalex.org/W4252326246","https://openalex.org/W4283447404","https://openalex.org/W4284710241","https://openalex.org/W4285282363","https://openalex.org/W4285490465","https://openalex.org/W4307812665","https://openalex.org/W4311887664","https://openalex.org/W4312282218","https://openalex.org/W4312903743","https://openalex.org/W4312999884","https://openalex.org/W4382239850","https://openalex.org/W4384154386","https://openalex.org/W4384304951","https://openalex.org/W4384345640","https://openalex.org/W4385562549","https://openalex.org/W4385571808","https://openalex.org/W4386076347","https://openalex.org/W4389524484","https://openalex.org/W4397032804","https://openalex.org/W4401812232","https://openalex.org/W4402670824","https://openalex.org/W4403536522","https://openalex.org/W6725533135","https://openalex.org/W6748774801","https://openalex.org/W6754601402","https://openalex.org/W6767260250","https://openalex.org/W6769627184","https://openalex.org/W6771917389","https://openalex.org/W6783227185","https://openalex.org/W6783266986","https://openalex.org/W6795460807","https://openalex.org/W6801751227","https://openalex.org/W6803322908","https://openalex.org/W6810874553","https://openalex.org/W6839247405","https://openalex.org/W6853699639","https://openalex.org/W6872839843"],"related_works":["https://openalex.org/W2182697532","https://openalex.org/W1517387344","https://openalex.org/W1544062218","https://openalex.org/W1964111631","https://openalex.org/W2021613224","https://openalex.org/W185550498","https://openalex.org/W2348203156","https://openalex.org/W2189076424","https://openalex.org/W2226868092","https://openalex.org/W2164928043"],"abstract_inverted_index":{"Pre-training":[0],"a":[1,18,39,102,184],"language":[2,36],"model":[3,122,155,199],"and":[4,14,31,58,71,178,188],"then":[5],"fine-tuning":[6],"it":[7],"has":[8],"shown":[9],"to":[10,99,171,219,233,237],"be":[11],"an":[12,86,196],"efficient":[13],"effective":[15],"technique":[16],"for":[17,101,209],"wide":[19],"range":[20],"of":[21,89,115,175,198],"code":[22,27,29,41,69,82,210],"intelligence":[23,83,211],"tasks,":[24,212],"such":[25,53],"as":[26,54,195],"generation,":[28],"summarization,":[30],"vulnerability":[32],"detection.":[33],"However,":[34],"pre-training":[35],"models":[37,66,161,170],"on":[38,80,204],"large-scale":[40],"corpus":[42],"is":[43,105],"compu-tationally":[44],"expensive.":[45],"Fortunately,":[46],"many":[47],"off-the-shelf":[48],"Pre-trained":[49],"Code":[50,59],"Models":[51],"(PCMs),":[52],"CodeBERT,":[55],"CodeT5,":[56],"CodeGen,":[57],"Llama,":[60],"have":[61],"been":[62],"released":[63],"publicly.":[64],"These":[65],"acquire":[67],"general":[68],"understanding":[70],"generation":[72],"capability":[73],"during":[74],"pre-training,":[75],"which":[76],"enhances":[77],"their":[78,164,193],"performance":[79,174,247],"downstream":[81],"tasks.":[84,251],"With":[85],"increasing":[87],"number":[88],"these":[90,138,150],"public":[91],"pre-trained":[92,160,176],"models,":[93,177],"selecting":[94],"the":[95,113,173,180,189],"most":[96],"suitable":[97],"one":[98],"reuse":[100],"specific":[103],"task":[104],"essential.":[106],"In":[107],"this":[108],"paper,":[109],"we":[110,152,167],"systematically":[111],"investigate":[112],"reusability":[114],"PCMs.":[116],"We":[117,201],"first":[118],"explore":[119,153],"three":[120],"intuitive":[121],"selection":[123,156,228,231],"methods":[124,229],"that":[125,137,158,226],"select":[126],"by":[127,149],"size,":[128],"training":[129],"data,":[130],"or":[131,144],"brute-force":[132,241],"fine-tuning.":[133],"Experimental":[134],"results":[135,224],"show":[136],"straightforward":[139],"techniques":[140],"either":[141],"perform":[142],"poorly":[143],"suffer":[145],"high":[146],"costs.":[147],"Motivated":[148],"findings,":[151],"learning-based":[154,227],"strategies":[157],"utilize":[159],"without":[162],"altering":[163],"parameters.":[165,222],"Specifically,":[166],"train":[168],"proxy":[169],"gauge":[172],"measure":[179],"distribution":[181],"deviation":[182],"between":[183],"model's":[185],"latent":[186],"features":[187],"task's":[190],"labels,":[191],"using":[192],"closeness":[194],"indicator":[197],"transferability.":[200],"conduct":[202],"experiments":[203],"100":[205,234],"widely-used":[206],"open-source":[207],"PCMs":[208],"with":[213,240,243],"sizes":[214],"ranging":[215],"from":[216],"42.5":[217],"million":[218],"3":[220],"billion":[221],"The":[223],"demonstrate":[225],"reduce":[230],"time":[232],"seconds,":[235],"compared":[236],"2,700":[238],"hours":[239],"fine-tuning,":[242],"less":[244],"than":[245],"6%":[246],"degradation":[248],"across":[249],"related":[250]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}