{"id":"https://openalex.org/W2972009176","doi":"https://doi.org/10.1109/access.2019.2938825","title":"Fast Code Clone Detection Based on Weighted Recursive Autoencoders","display_name":"Fast Code Clone Detection Based on Weighted Recursive Autoencoders","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2972009176","doi":"https://doi.org/10.1109/access.2019.2938825","mag":"2972009176"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2938825","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2938825","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08822436.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08822436.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064451977","display_name":"Jie Zeng","orcid":"https://orcid.org/0000-0003-0621-6550"},"institutions":[{"id":"https://openalex.org/I2800710378","display_name":"Naval University of Engineering","ror":"https://ror.org/056vyez31","country_code":"CN","type":"education","lineage":["https://openalex.org/I2800710378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zeng","raw_affiliation_strings":["College of Electronic Engineering, Naval University of Engineering, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-0621-6550","affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Naval University of Engineering, Wuhan, China","institution_ids":["https://openalex.org/I2800710378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071895699","display_name":"Kerong Ben","orcid":"https://orcid.org/0000-0001-5013-1947"},"institutions":[{"id":"https://openalex.org/I2800710378","display_name":"Naval University of Engineering","ror":"https://ror.org/056vyez31","country_code":"CN","type":"education","lineage":["https://openalex.org/I2800710378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kerong Ben","raw_affiliation_strings":["College of Electronic Engineering, Naval University of Engineering, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Naval University of Engineering, Wuhan, China","institution_ids":["https://openalex.org/I2800710378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023380073","display_name":"Xiaowei Li","orcid":"https://orcid.org/0000-0002-0874-814X"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Li","raw_affiliation_strings":["Jinghang Research Institute of Computing and Communication, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jinghang Research Institute of Computing and Communication, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110588532","display_name":"Xian Zhang","orcid":"https://orcid.org/0000-0002-7910-1562"},"institutions":[{"id":"https://openalex.org/I2800710378","display_name":"Naval University of Engineering","ror":"https://ror.org/056vyez31","country_code":"CN","type":"education","lineage":["https://openalex.org/I2800710378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhang","raw_affiliation_strings":["College of Electronic Engineering, Naval University of Engineering, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, Naval University of Engineering, Wuhan, China","institution_ids":["https://openalex.org/I2800710378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.272,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.93109507,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"7","issue":null,"first_page":"125062","last_page":"125078"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.998199999332428,"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":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.7624661922454834},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5486205816268921},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.47355738282203674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43530669808387756},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3773152232170105},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17599815130233765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7624661922454834},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5486205816268921},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.47355738282203674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43530669808387756},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3773152232170105},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17599815130233765},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2938825","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2938825","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08822436.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c480bdd6501a44a8bb0ad7a9a54c9f5c","is_oa":true,"landing_page_url":"https://doaj.org/article/c480bdd6501a44a8bb0ad7a9a54c9f5c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 125062-125078 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2938825","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2938825","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08822436.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972009176.pdf","grobid_xml":"https://content.openalex.org/works/W2972009176.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W71795751","https://openalex.org/W1567790484","https://openalex.org/W1614298861","https://openalex.org/W1990762361","https://openalex.org/W2041190309","https://openalex.org/W2065053490","https://openalex.org/W2103305545","https://openalex.org/W2109759383","https://openalex.org/W2128782367","https://openalex.org/W2128888088","https://openalex.org/W2138756793","https://openalex.org/W2147717514","https://openalex.org/W2158439356","https://openalex.org/W2162436321","https://openalex.org/W2163922914","https://openalex.org/W2172244770","https://openalex.org/W2250539671","https://openalex.org/W2282866165","https://openalex.org/W2427333829","https://openalex.org/W2511803001","https://openalex.org/W2526367648","https://openalex.org/W2578208870","https://openalex.org/W2621103691","https://openalex.org/W2634106992","https://openalex.org/W2741705590","https://openalex.org/W2757662681","https://openalex.org/W2767683547","https://openalex.org/W2767717989","https://openalex.org/W2807866521","https://openalex.org/W2883359218","https://openalex.org/W2899171197","https://openalex.org/W2919115771","https://openalex.org/W2963284996","https://openalex.org/W3105535951","https://openalex.org/W4301168982","https://openalex.org/W6602989467","https://openalex.org/W6633995546","https://openalex.org/W6636510571","https://openalex.org/W6695202613","https://openalex.org/W6727823000"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2377327490","https://openalex.org/W2560253012","https://openalex.org/W1524590520","https://openalex.org/W2412288087","https://openalex.org/W2371792548","https://openalex.org/W1697705604","https://openalex.org/W2419862115","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Code":[0],"cloning":[1],"considerably":[2],"facilitates":[3],"software":[4,14,131],"development":[5],"but":[6],"also":[7,224],"leads":[8],"to":[9,34,78,93,167,269],"recurring":[10],"bugs":[11],"and":[12,74,161,194,197,238,261],"other":[13],"quality":[15],"problems.":[16],"In":[17],"this":[18,141],"paper,":[19],"we":[20,61,84,112,143],"propose":[21],"a":[22,157],"fast":[23],"code":[24,36,48,119,266],"clone":[25,49,120,146,200],"detection":[26,147],"method":[27,54,180,223,254],"based":[28,185],"on":[29,175,186],"weighted":[30,68],"recursive":[31],"autoencoders":[32],"(RAE)":[33],"measure":[35],"similarity":[37],"at":[38],"the":[39,71,76,81,95,104,145,163,169,182,207,264],"function":[40],"level.":[41],"Different":[42],"from":[43],"manually":[44],"defining":[45],"features":[46,73],"for":[47,258],"detection,":[50],"our":[51,179,239,253],"deep":[52],"learning-based":[53],"can":[55,198],"automatically":[56],"learn":[57],"program":[58,63,72],"features.":[59],"First,":[60],"analyze":[62],"abstract":[64,90],"syntax":[65,91],"trees":[66,92],"using":[67],"RAE,":[69],"extract":[70],"encode":[75],"functions":[77,114],"vectors.":[79,221],"During":[80],"modeling":[82],"process,":[83],"consider":[85],"node":[86],"weight":[87],"information":[88,98],"in":[89,103,156,189,202,231],"increase":[94],"proportion":[96],"of":[97,108,191,263],"contributed":[99],"by":[100],"important":[101],"nodes":[102],"final":[105],"vector":[106,159],"representation":[107],"one":[109],"program.":[110],"Second,":[111],"report":[113],"with":[115],"similar":[116],"vectors":[117],"as":[118],"pairs.":[121],"The":[122],"second":[123],"phase":[124],"is":[125,267],"time":[126,171],"consuming":[127],"when":[128,214],"analyzing":[129],"large":[130],"systems":[132],"because":[133],"it":[134],"needs":[135],"quadratic":[136],"pairwise":[137,216],"comparisons.":[138],"To":[139],"solve":[140],"problem,":[142],"transform":[144],"problem":[148],"into":[149],"an":[150],"approximate":[151],"nearest":[152],"neighbors":[153],"search":[154],"(ANNS)":[155],"high-dimensional":[158],"set":[160],"use":[162],"navigating":[164],"spreading-out":[165],"graph":[166],"reduce":[168],"computational":[170],"complexity.":[172],"Experimental":[173],"results":[174],"BigCloneBench":[176],"show":[177],"that":[178],"outperforms":[181,225],"compared":[183,208],"algorithm":[184,209],"unweighted":[187],"RAE":[188],"terms":[190],"precision,":[192],"recall,":[193],"AUC":[195],"value":[196],"return":[199],"pairs":[201],"approximately":[203,211],"33":[204],"min,":[205],"while":[206],"requires":[210],"14":[212],"days":[213],"performing":[215],"comparisons":[217],"among":[218],"785,438":[219],"functions'":[220],"Our":[222],"many":[226],"prominent":[227],"tools,":[228],"including":[229],"Oreo,":[230],"detecting":[232],"Moderately":[233],"Type-3":[234],"or":[235],"Type-4":[236],"clones,":[237],"false":[240,249],"positive":[241],"rate":[242],"(FPR)":[243],"equals":[244],"0.055,":[245],"which":[246],"means":[247],"few":[248],"positives.":[250],"More":[251],"importantly,":[252],"has":[255],"no":[256],"need":[257],"labeled":[259],"data,":[260],"all":[262],"source":[265],"released":[268],"guarantee":[270],"experimental":[271],"reproducibility.":[272]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}