{"id":"https://openalex.org/W4409149672","doi":"https://doi.org/10.1145/3690624.3709263","title":"MGS3: A Multi-Granularity Self-Supervised Code Search Framework","display_name":"MGS3: A Multi-Granularity Self-Supervised Code Search Framework","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409149672","doi":"https://doi.org/10.1145/3690624.3709263"},"language":"en","primary_location":{"id":"doi:10.1145/3690624.3709263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709263","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3690624.3709263","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115604810","display_name":"Rui Li","orcid":"https://orcid.org/0009-0005-3657-1133"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Li","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-3657-1133","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104271404","display_name":"Junfeng Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Kang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-3898-0176","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453156","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-6956-5550"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6956-5550","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077791803","display_name":"Liyang He","orcid":"https://orcid.org/0000-0002-1609-0747"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyang He","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1609-0747","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867714","display_name":"Zheng Zhang","orcid":"https://orcid.org/0009-0002-8689-0763"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-8689-0763","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109774159","display_name":"Yunhao Sha","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhao Sha","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-9147-9604","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050061137","display_name":"Linbo Zhu","orcid":"https://orcid.org/0009-0003-6036-5095"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linbo Zhu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-6036-5095","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085496384","display_name":"Zhenya Huang","orcid":"https://orcid.org/0000-0003-1661-0420"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenya Huang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1661-0420","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02629612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"695","last_page":"706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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":0.9975000023841858,"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/T10028","display_name":"Topic Modeling","score":0.9900000095367432,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.890008807182312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.799199104309082},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5910793542861938},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34784621000289917},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2632787227630615}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.890008807182312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.799199104309082},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5910793542861938},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34784621000289917},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2632787227630615},{"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:10.1145/3690624.3709263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709263","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3690624.3709263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709263","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2516621648","https://openalex.org/W2606555609","https://openalex.org/W2788306232","https://openalex.org/W2884276923","https://openalex.org/W2887364112","https://openalex.org/W2949297108","https://openalex.org/W2955931418","https://openalex.org/W2962858109","https://openalex.org/W2964315653","https://openalex.org/W3021397474","https://openalex.org/W3034689979","https://openalex.org/W3035524453","https://openalex.org/W3086449553","https://openalex.org/W3098281910","https://openalex.org/W3155146092","https://openalex.org/W3168875417","https://openalex.org/W3176015924","https://openalex.org/W3196992070","https://openalex.org/W4205371973","https://openalex.org/W4205807230","https://openalex.org/W4221166942","https://openalex.org/W4238846128","https://openalex.org/W4292793914","https://openalex.org/W4293569092","https://openalex.org/W4362469857","https://openalex.org/W4385573211","https://openalex.org/W4385573657","https://openalex.org/W4389524421","https://openalex.org/W4393148034","https://openalex.org/W4396735336","https://openalex.org/W4396758529","https://openalex.org/W4403791620","https://openalex.org/W4403792529","https://openalex.org/W4404241960","https://openalex.org/W4404783208","https://openalex.org/W6816482620"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W2354431794"],"abstract_inverted_index":{"In":[0],"the":[1,39,68,81,158,169,197],"pursuit":[2],"of":[3,42,70,93,113,168,206],"enhancing":[4],"software":[5],"reusability":[6],"and":[7,75,116,149,175,216],"developer":[8],"productivity,":[9],"code":[10,21,36,43,62,77,83,104,117,128,189,203,221],"search":[11,105,190,204],"has":[12],"emerged":[13],"as":[14,73],"a":[15,102,122,135],"key":[16],"area,":[17],"aimed":[18],"at":[19],"retrieving":[20],"snippets":[22,78],"relevant":[23],"to":[24,56,164],"functionalities":[25],"based":[26],"on":[27,52,188],"natural":[28,58,114],"language":[29,59,115],"queries.":[30],"Despite":[31],"significant":[32],"progress":[33],"in":[34,45,87,202],"self-supervised":[35],"pre-training":[37],"utilizing":[38],"vast":[40],"amount":[41],"data":[44],"repositories,":[46],"existing":[47,219],"methods":[48],"have":[49,66],"primarily":[50],"focused":[51],"leveraging":[53],"contrastive":[54,126,159],"learning":[55,127,160],"align":[57],"with":[60,218],"function-level":[61,82],"snippets.":[63,118],"These":[64,209],"studies":[65],"overlooked":[67],"abundance":[69],"fine-grained":[71,151,173,181],"(such":[72],"block-level":[74],"statement-level)":[76],"prevalent":[79],"within":[80],"snippets,":[84],"which":[85,109,141],"results":[86],"suboptimal":[88],"performance":[89,201],"across":[90,192],"all":[91],"levels":[92],"granularity.":[94],"To":[95],"address":[96],"this":[97],"problem,":[98],"we":[99,120,162,184],"first":[100],"construct":[101,165],"multi-granularity":[103],"dataset":[106],"called":[107],"MGCodeSearchNet,":[108],"contains":[110],"536K+":[111],"pairs":[112],"Subsequently,":[119],"introduce":[121,176],"novel":[123],"Multi-Granularity":[124,137],"Self-Supervised":[125],"Search":[129],"framework":[130,198],"(MGS3).":[131],"First,":[132],"MGS3":[133],"features":[134],"Hierarchical":[136],"Representation":[138],"module":[139],"(HMGR),":[140],"leverages":[142],"syntactic":[143],"structural":[144],"relationships":[145],"for":[146,172,180],"hierarchical":[147],"representation":[148,222],"aggregates":[150],"information":[152],"into":[153],"coarser-grained":[154],"representations.":[155],"Then,":[156],"during":[157],"phase,":[161],"endeavor":[163],"positive":[166],"samples":[167,179],"same":[170],"granularity":[171],"code,":[174],"in-function":[177],"negative":[178],"code.":[182],"Finally,":[183],"conduct":[185],"extensive":[186],"experiments":[187,210],"benchmarks":[191],"various":[193],"granularities,":[194],"demonstrating":[195],"that":[196],"exhibits":[199],"outstanding":[200],"tasks":[205],"multiple":[207],"granularities.":[208],"also":[211],"showcase":[212],"its":[213],"model-agnostic":[214],"nature":[215],"compatibility":[217],"pre-trained":[220],"models.":[223]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}