{"id":"https://openalex.org/W4391579684","doi":"https://doi.org/10.1145/3597503.3608136","title":"FAIR: Flow Type-Aware Pre-Training of Compiler Intermediate Representations","display_name":"FAIR: Flow Type-Aware Pre-Training of Compiler Intermediate Representations","publication_year":2024,"publication_date":"2024-02-06","ids":{"openalex":"https://openalex.org/W4391579684","doi":"https://doi.org/10.1145/3597503.3608136"},"language":"en","primary_location":{"id":"doi:10.1145/3597503.3608136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597503.3608136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/9265","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061689324","display_name":"Changan Niu","orcid":"https://orcid.org/0000-0003-4358-5451"},"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":true,"raw_author_name":"Changan Niu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, 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":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102732054","display_name":"Vincent Ng","orcid":"https://orcid.org/0000-0001-8237-429X"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Ng","raw_affiliation_strings":["Human Language Technology Research Institute, University of Texas at Dallas, Richardson, TX 75083-0688, Dallas, Texas, United States of America"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Research Institute, University of Texas at Dallas, Richardson, TX 75083-0688, Dallas, Texas, United States of America","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081036622","display_name":"David Lo","orcid":"https://orcid.org/0000-0002-4367-7201"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"David Lo","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037431446","display_name":"Bin Luo","orcid":"https://orcid.org/0000-0002-7609-4838"},"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":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061689324"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":3.0537,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.91854941,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"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/T10260","display_name":"Software Engineering Research","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9943000078201294,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8706645965576172},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5631740689277649},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5496172308921814},{"id":"https://openalex.org/keywords/control-flow-graph","display_name":"Control flow graph","score":0.5468990802764893},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5422488451004028},{"id":"https://openalex.org/keywords/bytecode","display_name":"Bytecode","score":0.5128265023231506},{"id":"https://openalex.org/keywords/data-flow-analysis","display_name":"Data-flow analysis","score":0.4984431266784668},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.49697592854499817},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.46287965774536133},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4619711935520172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3985159397125244},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36292773485183716},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.30813735723495483},{"id":"https://openalex.org/keywords/data-flow-diagram","display_name":"Data flow diagram","score":0.277504563331604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8706645965576172},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5631740689277649},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5496172308921814},{"id":"https://openalex.org/C27458966","wikidata":"https://www.wikidata.org/wiki/Q1187693","display_name":"Control flow graph","level":2,"score":0.5468990802764893},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5422488451004028},{"id":"https://openalex.org/C2779818221","wikidata":"https://www.wikidata.org/wiki/Q837330","display_name":"Bytecode","level":3,"score":0.5128265023231506},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.4984431266784668},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.49697592854499817},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.46287965774536133},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4619711935520172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3985159397125244},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36292773485183716},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.30813735723495483},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.277504563331604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3597503.3608136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597503.3608136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-10265","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/9265","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-10265","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/9265","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceeding Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4462563244","display_name":null,"funder_award_id":"2034508","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5332036567","display_name":null,"funder_award_id":"NRF-NRFI08-2022-0002","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G7169835300","display_name":null,"funder_award_id":"NRF-NRFI08-2022-0002","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G875168909","display_name":null,"funder_award_id":"NRF-NRFI08-2022","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1898843043","https://openalex.org/W1982020565","https://openalex.org/W1989562524","https://openalex.org/W2282866165","https://openalex.org/W2612690371","https://openalex.org/W2740721704","https://openalex.org/W2892181857","https://openalex.org/W2962784628","https://openalex.org/W2981852735","https://openalex.org/W2998496395","https://openalex.org/W3007205676","https://openalex.org/W3034999214","https://openalex.org/W3039500550","https://openalex.org/W3086481683","https://openalex.org/W3096804376","https://openalex.org/W3098380913","https://openalex.org/W3098605233","https://openalex.org/W3101543043","https://openalex.org/W3116350821","https://openalex.org/W3121707215","https://openalex.org/W3161997752","https://openalex.org/W3165977309","https://openalex.org/W3169575312","https://openalex.org/W3170092793","https://openalex.org/W3175836671","https://openalex.org/W3198685994","https://openalex.org/W3212637752","https://openalex.org/W4221147210","https://openalex.org/W4221166942","https://openalex.org/W4224246371","https://openalex.org/W4281706128","https://openalex.org/W4282017563","https://openalex.org/W4284697810","https://openalex.org/W4284896159","https://openalex.org/W4287123803","https://openalex.org/W4287887329","https://openalex.org/W4288089799","https://openalex.org/W4290944058","https://openalex.org/W4312709113","https://openalex.org/W6784702030","https://openalex.org/W6839395506"],"related_works":["https://openalex.org/W2168933008","https://openalex.org/W2992753978","https://openalex.org/W1999711970","https://openalex.org/W2166895275","https://openalex.org/W2151163382","https://openalex.org/W2998775986","https://openalex.org/W1484884871","https://openalex.org/W1971022286","https://openalex.org/W1565879960","https://openalex.org/W2876884816"],"abstract_inverted_index":{"While":[0],"the":[1,75,140,149],"majority":[2],"of":[3,72,113,142,152],"existing":[4],"pre-trained":[5,101],"models":[6,37],"from":[7,30],"code":[8,11,15],"learn":[9,139],"source":[10],"features":[12,41],"such":[13,42],"as":[14,43],"tokens":[16],"and":[17,46,60,66,74,85,88,123,126,148],"abstract":[18],"syntax":[19],"trees,":[20],"there":[21],"are":[22],"some":[23],"other":[24],"works":[25],"that":[26,105,131,157],"focus":[27],"on":[28,163],"learning":[29],"compiler":[31],"intermediate":[32],"representations":[33],"(IRs).":[34],"Existing":[35],"IR-based":[36],"typically":[38],"utilize":[39],"IR":[40,104,114,143],"instructions,":[44],"control":[45],"data":[47],"flow":[48,145],"graphs":[49],"(CDFGs),":[50],"call":[51],"graphs,":[52],"etc.":[53],"However,":[54],"these":[55,93],"methods":[56],"confuse":[57],"variable":[58],"nodes":[59,62],"instruction":[61],"in":[63],"a":[64,98,109],"CDFG":[65],"fail":[67,80],"to":[68,81,119,135,138],"distinguish":[69],"different":[70],"types":[71],"flows,":[73],"neural":[76],"networks":[77],"they":[78],"use":[79],"capture":[82],"long-distance":[83],"dependencies":[84],"have":[86],"over-smoothing":[87],"over-squashing":[89,122],"problems.":[90],"To":[91],"address":[92,120],"weaknesses,":[94],"we":[95,132],"propose":[96,134],"FAIR,":[97],"Flow":[99],"type-Aware":[100],"model":[102],"for":[103],"involves":[106],"employing":[107],"(1)":[108],"novel":[110],"input":[111],"representation":[112,151],"programs;":[115],"(2)":[116],"Graph":[117],"Transformer":[118],"over-smoothing,":[121],"long-dependencies":[124],"problems;":[125],"(3)":[127],"five":[128],"pre-training":[129],"tasks":[130],"specifically":[133],"enable":[136],"FAIR":[137,158],"semantics":[141],"tokens,":[144],"type":[146],"information,":[147],"overall":[150],"IR.":[153],"Experimental":[154],"results":[155,162],"show":[156],"can":[159],"achieve":[160],"state-of-the-art":[161],"four":[164],"code-related":[165],"downstream":[166],"tasks.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}