{"id":"https://openalex.org/W7131081605","doi":"https://doi.org/10.1109/cgo68049.2026.11395223","title":"FORTE: Online DataFrame Query Optimizer","display_name":"FORTE: Online DataFrame Query Optimizer","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7131081605","doi":"https://doi.org/10.1109/cgo68049.2026.11395223"},"language":null,"primary_location":{"id":"doi:10.1109/cgo68049.2026.11395223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo68049.2026.11395223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126631951","display_name":"Yoonho Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yoonho Choi","raw_affiliation_strings":["POSTECH,Pohang,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH,Pohang,Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041425645","display_name":"Kyoungtae Lee","orcid":"https://orcid.org/0000-0002-4605-1415"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyoungtae Lee","raw_affiliation_strings":["Seoul National University,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317748","display_name":"Minji Kim","orcid":"https://orcid.org/0000-0002-2617-686X"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minji Kim","raw_affiliation_strings":["Ewha Womans University,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034858357","display_name":"Hyungsoo Jung","orcid":"https://orcid.org/0000-0002-5376-7200"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungsoo Jung","raw_affiliation_strings":["Seoul National University,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005051912","display_name":"Hyojin Sung","orcid":"https://orcid.org/0000-0002-3036-6180"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyojin Sung","raw_affiliation_strings":["Seoul National University,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5126631951"],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3036129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.18880000710487366,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.18880000710487366,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.13660000264644623,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.060499999672174454,"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/rewriting","display_name":"Rewriting","score":0.6880000233650208},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.5389000177383423},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.4982999861240387},{"id":"https://openalex.org/keywords/lazy-evaluation","display_name":"Lazy evaluation","score":0.4699000120162964},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45879998803138733},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.44859999418258667},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.4327999949455261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299000263214111},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.6880000233650208},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.656499981880188},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C128099668","wikidata":"https://www.wikidata.org/wiki/Q573952","display_name":"Lazy evaluation","level":3,"score":0.4699000120162964},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39879998564720154},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C128838566","wikidata":"https://www.wikidata.org/wiki/Q275603","display_name":"Logic programming","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo68049.2026.11395223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo68049.2026.11395223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1558370006","https://openalex.org/W2106771621","https://openalex.org/W2122054842","https://openalex.org/W2185907055","https://openalex.org/W2245493112","https://openalex.org/W2527672088","https://openalex.org/W2625141509","https://openalex.org/W2783734440","https://openalex.org/W2798416929","https://openalex.org/W2949054050","https://openalex.org/W3082494217","https://openalex.org/W3202653805","https://openalex.org/W4205675279","https://openalex.org/W4210382907","https://openalex.org/W4246166885","https://openalex.org/W4297319618","https://openalex.org/W4366492480","https://openalex.org/W4381326897","https://openalex.org/W4384129442","https://openalex.org/W4393183688","https://openalex.org/W4399668283","https://openalex.org/W4400909714","https://openalex.org/W4403223243","https://openalex.org/W4404181467","https://openalex.org/W4407356002","https://openalex.org/W4411403274","https://openalex.org/W4413980089"],"related_works":[],"abstract_inverted_index":{"DataFrame":[0,59,69,155],"libraries":[1,60],"are":[2],"widely":[3],"adopted":[4],"in":[5,39],"data":[6],"science":[7],"for":[8],"their":[9,14],"flexible,":[10],"Pythonic":[11],"interfaces,":[12],"but":[13],"fragmented":[15],"APIs":[16],"and":[17,43,74,86,102,117,125,145,157],"unstructured":[18],"query":[19,54],"patterns":[20],"limit":[21],"systematic":[22],"optimization.":[23],"Existing":[24],"work":[25],"has":[26],"explored":[27],"parallel":[28],"execution":[29],"or":[30],"SQL-style":[31],"logical":[32],"rewrites,":[33],"yet":[34],"these":[35,107],"approaches":[36],"fall":[37],"short":[38],"capturing":[40],"DataFrame-specific":[41],"semantics":[42,70],"Python":[44],"control-flow":[45],"context.":[46],"We":[47],"present":[48],"FORTE,":[49],"the":[50],"first":[51],"online,":[52,148],"source-to-source":[53],"optimizer":[55],"that":[56,130,147],"unifies":[57],"multiple":[58],"under":[61],"a":[62,97],"shared":[63],"intermediate":[64],"representation":[65],"(DFL).":[66],"DFL":[67],"makes":[68],"explicit,":[71],"enabling":[72,160],"composable":[73],"portable":[75],"rewriting":[76,150],"rules":[77],"such":[78],"as":[79],"user-defined":[80],"function":[81],"(UDF)":[82],"lifting/lowering,":[83],"loop":[84],"lifting,":[85],"API":[87],"tuning,":[88],"alongside":[89],"classical":[90],"rewrites":[91,108],"(e.g.,":[92],"predicate":[93],"pushdown).":[94],"FORTE":[95,131],"employs":[96],"lightweight,":[98],"learned":[99],"cost":[100],"model":[101],"greedy":[103],"search":[104],"to":[105,136],"apply":[106],"with":[109],"negligible":[110],"overhead,":[111],"while":[112,159],"supporting":[113],"both":[114],"intra-library":[115],"optimization":[116],"cross-library":[118,161],"transpilation.":[119],"Our":[120],"evaluation":[121],"on":[122,139],"TPC-H":[123],"workloads":[124,128],"real-world":[126],"Kaggle/GitHub":[127],"shows":[129],"consistently":[132],"delivers":[133],"substantial":[134],"speedups\u2014up":[135],"52.53\u00d7":[137],"(3.7\u00d7":[138],"average)":[140],"across":[141],"Pandas,":[142],"Modin,":[143],"Polars,":[144],"Pandas-on-Spark\u2014demonstrating":[146],"IR-guided":[149],"can":[151],"significantly":[152],"outperform":[153],"existing":[154],"engines":[156],"rewriters,":[158],"retargetability.":[162]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-02-24T00:00:00"}