{"id":"https://openalex.org/W4283751459","doi":"https://doi.org/10.1145/3540250.3549094","title":"Diet code is healthy: simplifying programs for pre-trained models of code","display_name":"Diet code is healthy: simplifying programs for pre-trained models of code","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4283751459","doi":"https://doi.org/10.1145/3540250.3549094"},"language":"en","primary_location":{"id":"doi:10.1145/3540250.3549094","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3540250.3549094","pdf_url":null,"source":{"id":"https://openalex.org/S4363608883","display_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.14390","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100683815","display_name":"Zhaowei Zhang","orcid":"https://orcid.org/0000-0002-6686-2995"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaowei Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412587","display_name":"Hong\u2010yu Zhang","orcid":"https://orcid.org/0000-0001-5142-5277"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hongyu Zhang","raw_affiliation_strings":["University of Newcastle, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Newcastle, Australia","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045672909","display_name":"Beijun Shen","orcid":"https://orcid.org/0000-0001-8370-3956"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beijun Shen","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033286111","display_name":"Xiaodong Gu","orcid":"https://orcid.org/0000-0002-0529-6408"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Gu","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1073","last_page":"1084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.996999979019165,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8330792784690857},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6941649913787842},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5457463264465332},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5250037908554077},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.48972609639167786},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.47216862440109253},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4486081600189209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43140196800231934},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4308132529258728},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.4270623028278351},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4234943687915802},{"id":"https://openalex.org/keywords/quadratic-growth","display_name":"Quadratic growth","score":0.41029149293899536},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21507304906845093},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18762236833572388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330792784690857},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6941649913787842},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5457463264465332},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5250037908554077},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.48972609639167786},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.47216862440109253},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4486081600189209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43140196800231934},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4308132529258728},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.4270623028278351},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4234943687915802},{"id":"https://openalex.org/C195956108","wikidata":"https://www.wikidata.org/wiki/Q7268362","display_name":"Quadratic growth","level":2,"score":0.41029149293899536},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21507304906845093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18762236833572388},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3540250.3549094","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3540250.3549094","pdf_url":null,"source":{"id":"https://openalex.org/S4363608883","display_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.14390","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.14390","pdf_url":"https://arxiv.org/pdf/2206.14390","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:uon:53919","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.13/1494926","pdf_url":null,"source":{"id":"https://openalex.org/S4377196471","display_name":"NOVA (University of Newcastle Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78757542","host_organization_name":"University of Newcastle Australia","host_organization_lineage":["https://openalex.org/I78757542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.14390","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.14390","pdf_url":"https://arxiv.org/pdf/2206.14390","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1756752431","display_name":null,"funder_award_id":"62102244","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1644882639","https://openalex.org/W1776713878","https://openalex.org/W2060055745","https://openalex.org/W2113610359","https://openalex.org/W2133564696","https://openalex.org/W2136296681","https://openalex.org/W2138756793","https://openalex.org/W2157331557","https://openalex.org/W2170224888","https://openalex.org/W2250473257","https://openalex.org/W2342696155","https://openalex.org/W2511803001","https://openalex.org/W2541061885","https://openalex.org/W2766839578","https://openalex.org/W2783538964","https://openalex.org/W2892181857","https://openalex.org/W2896457183","https://openalex.org/W2914120296","https://openalex.org/W2955426500","https://openalex.org/W2963499994","https://openalex.org/W2964150020","https://openalex.org/W2964322208","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2978017171","https://openalex.org/W2981852735","https://openalex.org/W2998183051","https://openalex.org/W2999450509","https://openalex.org/W3034999214","https://openalex.org/W3098605233","https://openalex.org/W3100105221","https://openalex.org/W3118485687","https://openalex.org/W3126675481","https://openalex.org/W3146720657","https://openalex.org/W3161997752","https://openalex.org/W3168488662","https://openalex.org/W3170092793","https://openalex.org/W3171750540","https://openalex.org/W3176740355","https://openalex.org/W3180037928","https://openalex.org/W3194682511","https://openalex.org/W3198685994","https://openalex.org/W4205596491","https://openalex.org/W4210440021","https://openalex.org/W4221167729","https://openalex.org/W4246553962","https://openalex.org/W4287824654","https://openalex.org/W4288089799","https://openalex.org/W4308731473","https://openalex.org/W4309386164","https://openalex.org/W4385245566","https://openalex.org/W4394638297"],"related_works":["https://openalex.org/W2084086280","https://openalex.org/W2027198738","https://openalex.org/W2397767885","https://openalex.org/W3082178636","https://openalex.org/W2062514649","https://openalex.org/W2083114070","https://openalex.org/W237421766","https://openalex.org/W3013712002","https://openalex.org/W2004392729","https://openalex.org/W4238270958"],"abstract_inverted_index":{"Pre-trained":[0],"code":[1],"representation":[2],"models":[3,73],"such":[4,52],"as":[5,53],"CodeBERT":[6,41,83,137],"have":[7],"demonstrated":[8],"superior":[9],"performance":[10],"in":[11,23,115,143],"a":[12,112],"variety":[13],"of":[14,29,36,48,70,82],"software":[15],"engineering":[16],"tasks,":[17],"yet":[18],"they":[19],"are":[20],"often":[21],"heavy":[22],"complexity,":[24],"quadratically":[25],"with":[26,84,138],"the":[27,30,79,103,116,121],"length":[28],"input":[31,80],"sequence.":[32],"Our":[33],"empirical":[34],"analysis":[35],"CodeBERT's":[37],"attention":[38,44,105],"reveals":[39],"that":[40,96,101,131],"pays":[42],"more":[43],"to":[45,136],"certain":[46],"types":[47],"tokens":[49,100],"and":[50,55,92,99,145],"statements":[51,98],"keywords":[54],"data-relevant":[56],"statements.":[57],"Based":[58],"on":[59,126],"these":[60],"findings,":[61],"we":[62],"propose":[63],"DietCode,":[64],"which":[65],"aims":[66],"at":[67],"lightweight":[68],"leverage":[69],"large":[71],"pre-trained":[72],"for":[74],"source":[75],"code.":[76],"DietCode":[77,132],"simplifies":[78],"program":[81],"three":[85],"strategies,":[86],"namely,":[87],"word":[88],"dropout,":[89],"frequency":[90],"filtering,":[91],"an":[93],"attention-based":[94],"strategy":[95],"selects":[97],"receive":[102],"most":[104],"weights":[106],"during":[107],"pre-training.":[108],"Hence,":[109],"it":[110],"gives":[111],"substantial":[113],"reduction":[114],"computational":[117,141],"cost":[118,142],"without":[119],"hampering":[120],"model":[122],"performance.":[123],"Experimental":[124],"results":[125,135],"two":[127],"downstream":[128],"tasks":[129],"show":[130],"provides":[133],"comparable":[134],"40%":[139],"less":[140],"fine-tuning":[144],"testing.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}