{"id":"https://openalex.org/W4403336452","doi":"https://doi.org/10.1145/3695994","title":"Effective Hard Negative Mining for Contrastive Learning-Based Code Search","display_name":"Effective Hard Negative Mining for Contrastive Learning-Based Code Search","publication_year":2024,"publication_date":"2024-10-11","ids":{"openalex":"https://openalex.org/W4403336452","doi":"https://doi.org/10.1145/3695994"},"language":"en","primary_location":{"id":"doi:10.1145/3695994","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695994","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695994","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3695994","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012555354","display_name":"Fan Ye","orcid":"https://orcid.org/0000-0003-3584-9920"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Fan","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology at Nanjing University, Nanjing, China","National Key Laboratory for Novel Software Technology at Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0003-3584-9920","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology at Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology at Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103039853","display_name":"Chuanyi Li","orcid":"https://orcid.org/0000-0001-9270-5072"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanyi Li","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology at Nanjing University, Nanjing, China","National Key Laboratory for Novel Software Technology at Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0001-9270-5072","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology at Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology at Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075214885","display_name":"Jidong Ge","orcid":"https://orcid.org/0000-0003-1773-0942"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Ge","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology at Nanjing University, Nanjing, China","National Key Laboratory for Novel Software Technology at Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0003-1773-0942","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology at Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology at Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028716858","display_name":"LiGuo Huang","orcid":"https://orcid.org/0000-0001-7790-0195"},"institutions":[{"id":"https://openalex.org/I178169726","display_name":"Southern Methodist University","ror":"https://ror.org/042tdr378","country_code":"US","type":"education","lineage":["https://openalex.org/I178169726"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"LiGuo Huang","raw_affiliation_strings":["Department of Computer Science, Southern Methodist University, Dallas, TX, USA","Department of Computer Science, Southern Methodist University, USA"],"raw_orcid":"https://orcid.org/0000-0001-7790-0195","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Southern Methodist University, Dallas, TX, USA","institution_ids":["https://openalex.org/I178169726"]},{"raw_affiliation_string":"Department of Computer Science, Southern Methodist University, USA","institution_ids":["https://openalex.org/I178169726"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bin Luo","orcid":"https://orcid.org/0009-0001-1102-9584"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Luo","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology at Nanjing University, Nanjing, China","National Key Laboratory for Novel Software Technology at Nanjing University, China"],"raw_orcid":"https://orcid.org/0009-0001-1102-9584","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology at Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology at Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5583,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.91758954,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"34","issue":"3","first_page":"1","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9916999936103821,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8343806862831116},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4252539277076721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33142924308776855},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25500887632369995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343806862831116},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4252539277076721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33142924308776855},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25500887632369995},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695994","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695994","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695994","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3695994","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695994","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695994","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G8733650287","display_name":null,"funder_award_id":"BK20201250","funder_id":"https://openalex.org/F4320334982","funder_display_name":"Basic Research Program of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320334982","display_name":"Basic Research Program of Jiangsu Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403336452.pdf"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W1977971855","https://openalex.org/W1986601961","https://openalex.org/W2014755981","https://openalex.org/W2042803716","https://openalex.org/W2043909051","https://openalex.org/W2050372846","https://openalex.org/W2058724488","https://openalex.org/W2065053490","https://openalex.org/W2069065514","https://openalex.org/W2097001189","https://openalex.org/W2111909698","https://openalex.org/W2122401044","https://openalex.org/W2129384880","https://openalex.org/W2247374552","https://openalex.org/W2282866165","https://openalex.org/W2293624369","https://openalex.org/W2547405428","https://openalex.org/W2547932336","https://openalex.org/W2560674852","https://openalex.org/W2794601162","https://openalex.org/W2805788202","https://openalex.org/W2963341956","https://openalex.org/W2963391195","https://openalex.org/W2963879841","https://openalex.org/W2968179027","https://openalex.org/W2981852735","https://openalex.org/W3014339000","https://openalex.org/W3014451403","https://openalex.org/W3026732421","https://openalex.org/W3033748891","https://openalex.org/W3034781633","https://openalex.org/W3034999214","https://openalex.org/W3035524453","https://openalex.org/W3036320503","https://openalex.org/W3038572442","https://openalex.org/W3083784942","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3098468692","https://openalex.org/W3098605233","https://openalex.org/W3099700870","https://openalex.org/W3108032709","https://openalex.org/W3114632476","https://openalex.org/W3121707215","https://openalex.org/W3126104791","https://openalex.org/W3155146092","https://openalex.org/W3155895380","https://openalex.org/W3156636935","https://openalex.org/W3161997752","https://openalex.org/W3170092793","https://openalex.org/W3172854437","https://openalex.org/W3176015924","https://openalex.org/W3188982020","https://openalex.org/W3198188208","https://openalex.org/W3198685994","https://openalex.org/W4205371973","https://openalex.org/W4213009331","https://openalex.org/W4221166942","https://openalex.org/W4225407062","https://openalex.org/W4225576545","https://openalex.org/W4284666445","https://openalex.org/W4284679990","https://openalex.org/W4284697810","https://openalex.org/W4286910387","https://openalex.org/W4288089799","https://openalex.org/W4372269994","https://openalex.org/W4384345795","https://openalex.org/W4386075908","https://openalex.org/W4389519352","https://openalex.org/W4393154896"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Background":[0],".":[1,160,234,324],"Code":[2],"search":[3,26,40,246,337,368],"aims":[4],"to":[5,43,67,75,92,119,156,180,259,282,294,317],"find":[6],"the":[7,45,53,59,93,103,109,121,132,141,181,203,223,228,237,257,276,296,303,318,327,366,370],"most":[8,280,292],"relevant":[9],"code":[10,25,30,39,49,56,69,100,125,176,245,336,349,353,367,394,398,412],"snippet":[11],"in":[12,171,202,275,393,407],"a":[13,18,151,165,242,286],"large":[14,152,335],"codebase":[15,277],"based":[16],"on":[17,334],"given":[19],"natural":[20],"language":[21],"query.":[22,51],"An":[23],"accurate":[24],"engine":[27],"can":[28],"increase":[29,140],"reuse":[31],"and":[32,50,71,126,130,212,352,379,384,397,411],"improve":[33,302],"programming":[34,341,409],"efficiency.":[35],"The":[36,85,113],"focus":[37],"of":[38,48,55,61,87,95,115,143,167,184,306,329,374],"is":[41,90,118,163],"how":[42],"represent":[44,68,76],"semantic":[46,77,88,187,200,231,425],"similarity":[47,78,122,133],"With":[52],"development":[54],"pre-trained":[57],"models,":[58],"pattern":[60],"using":[62,72,172],"numeric":[63],"feature":[64],"vectors":[65,201],"(embeddings)":[66],"semantics":[70],"vector":[73],"distance":[74],"has":[79,388],"replaced":[80],"traditional":[81],"string":[82],"matching":[83,124],"methods.":[84],"quality":[86],"representations":[89,188],"critical":[91],"effectiveness":[94,328],"downstream":[96],"tasks":[97,348],"such":[98],"as":[99,343,345],"search.":[101],"Currently,":[102],"state-of-the-art":[104],"(SOTA)":[105],"learning":[106,111,117,148,244,304],"method":[107,404],"uses":[108],"contrastive":[110,116,147,243,269],"paradigm.":[112],"objective":[114],"maximize":[120],"between":[123,134,427],"query":[127],"(positive":[128],"samples)":[129],"minimize":[131],"mismatched":[135],"pairs":[136],"(negative":[137],"samples).":[138],"To":[139,235,255,301,325],"reusing":[142],"negative":[144,173,185,229,250,266,273,289,307,315],"samples,":[145,186],"prior":[146],"approaches":[149],"use":[150],"queue":[153],"(memory":[154],"bank)":[155],"store":[157],"embeddings.":[158],"Problem":[159],"However,":[161],"there":[162],"still":[164],"lot":[166],"room":[168],"for":[169,175,216],"improvement":[170],"examples":[174,267,274,290,316],"search:":[177],"\u2460":[178],"Due":[179],"random":[182],"selection":[183],"learned":[189],"by":[190,381],"existing":[191],"models":[192],"cannot":[193,225],"distinguish":[194,260],"similar":[195,261,281,346,428],"codes":[196],"well.":[197],"\u2461":[198],"Since":[199],"memory":[204],"bank":[205],"are":[206,272,279,291],"reused":[207],"from":[208],"previous":[209],"inference":[210],"results":[211,357],"then":[213],"directly":[214],"used":[215],"loss":[217],"function":[218],"calculation":[219],"without":[220],"gradient":[221,320],"descent,":[222],"model":[224,247,258,297,361,421],"effectively":[226,422],"learn":[227],"sample":[230],"information.":[232],"Method":[233],"solve":[236],"above":[238],"problems,":[239],"we":[240,263,311,331],"propose":[241],"with":[248,339],"hard":[249,265,288,314],"mining":[251],"called":[252],"CoCoHaNeRe:":[253],"\u2776":[254],"enable":[256],"codes,":[262],"introduce":[264],"into":[268],"training,":[270,310],"which":[271],"that":[278,359,419],"positive":[283],"examples.":[284],"As":[285],"result,":[287],"likely":[293],"make":[295,298],"mistakes.":[299],"\u2777":[300],"efficiency":[305],"samples":[308],"during":[309],"add":[312],"all":[313],"model's":[319],"descent":[321],"process.":[322],"Result":[323],"verify":[326],"CoCoHaNeRe,":[330],"conducted":[332],"experiments":[333],"datasets":[338],"six":[340],"languages,":[342],"well":[344,406],"retrieval":[347],"clone":[350,395],"detection":[351,396],"question":[354,399],"answering.":[355,400],"Experimental":[356],"show":[358],"our":[360,403,420],"achieves":[362],"SOTA":[363],"performance.":[364],"In":[365,401],"task,":[369],"average":[371],"MRR":[372],"score":[373],"CoCoHaNeRe":[375],"exceeds":[376],"CodeBERT,":[377],"GraphCodeBERT,":[378],"UniXcoder":[380],"11.25%,":[382],"8.13%,":[383],"7.38%,":[385],"respectively.":[386],"It":[387],"also":[389],"made":[390],"great":[391],"progress":[392],"addition,":[402],"performs":[405],"different":[408],"languages":[410],"pre-training":[413],"models.":[414],"Furthermore,":[415],"qualitative":[416],"analysis":[417],"shows":[418],"distinguishes":[423],"high-order":[424],"differences":[426],"codes.":[429]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}