{"id":"https://openalex.org/W4294811585","doi":"https://doi.org/10.1109/cec55065.2022.9870337","title":"Effects of the Training Set Size: A Comparison of Standard and Down-Sampled Lexicase Selection in Program Synthesis","display_name":"Effects of the Training Set Size: A Comparison of Standard and Down-Sampled Lexicase Selection in Program Synthesis","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4294811585","doi":"https://doi.org/10.1109/cec55065.2022.9870337"},"language":"en","primary_location":{"id":"doi:10.1109/cec55065.2022.9870337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec55065.2022.9870337","pdf_url":null,"source":{"id":"https://openalex.org/S4363605353","display_name":"2022 IEEE Congress on Evolutionary Computation (CEC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Congress on Evolutionary Computation (CEC)","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/A5073338685","display_name":"Dirk Schweim","orcid":"https://orcid.org/0000-0002-8629-0285"},"institutions":[{"id":"https://openalex.org/I108806672","display_name":"Baden-Wuerttemberg Cooperative State University","ror":"https://ror.org/02xdzy536","country_code":"DE","type":"education","lineage":["https://openalex.org/I108806672"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dirk Schweim","raw_affiliation_strings":["Baden-Wuerttemberg Cooperative State University,Dept. of Information Systems,Heidenheim,Germany","Dept. of Information Systems, Baden-Wuerttemberg Cooperative State University, Heidenheim, Germany"],"affiliations":[{"raw_affiliation_string":"Baden-Wuerttemberg Cooperative State University,Dept. of Information Systems,Heidenheim,Germany","institution_ids":["https://openalex.org/I108806672"]},{"raw_affiliation_string":"Dept. of Information Systems, Baden-Wuerttemberg Cooperative State University, Heidenheim, Germany","institution_ids":["https://openalex.org/I108806672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066837192","display_name":"Dominik Sobania","orcid":"https://orcid.org/0000-0001-8873-7143"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Sobania","raw_affiliation_strings":["Johannes Gutenberg University Mainz,Dept. of Information Systems,Mainz,Germany","Dept. of Information Systems, Johannes Gutenberg University Mainz, Mainz, Germany"],"affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University Mainz,Dept. of Information Systems,Mainz,Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Dept. of Information Systems, Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035443886","display_name":"Franz Rothlauf","orcid":"https://orcid.org/0000-0003-3376-427X"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Franz Rothlauf","raw_affiliation_strings":["Johannes Gutenberg University Mainz,Dept. of Information Systems,Mainz,Germany","Dept. of Information Systems, Johannes Gutenberg University Mainz, Mainz, Germany"],"affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University Mainz,Dept. of Information Systems,Mainz,Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Dept. of Information Systems, Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073338685"],"corresponding_institution_ids":["https://openalex.org/I108806672"],"apc_list":null,"apc_paid":null,"fwci":1.0388,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78425986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9997000098228455,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9878000020980835,"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"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9775000214576721,"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/overfitting","display_name":"Overfitting","score":0.9258476495742798},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.7654688954353333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7648947238922119},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6515380144119263},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.638705849647522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.602604329586029},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5423839688301086},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5393748879432678},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5383459329605103},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45509785413742065},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.443887859582901},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.43704575300216675},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4178253412246704},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16154104471206665},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12763285636901855},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11664652824401855}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9258476495742798},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.7654688954353333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648947238922119},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6515380144119263},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.638705849647522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.602604329586029},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5423839688301086},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5393748879432678},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5383459329605103},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45509785413742065},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.443887859582901},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.43704575300216675},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4178253412246704},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16154104471206665},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12763285636901855},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11664652824401855},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cec55065.2022.9870337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec55065.2022.9870337","pdf_url":null,"source":{"id":"https://openalex.org/S4363605353","display_name":"2022 IEEE Congress on Evolutionary Computation (CEC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W32282251","https://openalex.org/W47557113","https://openalex.org/W1482827835","https://openalex.org/W1483736078","https://openalex.org/W1576818901","https://openalex.org/W1593481303","https://openalex.org/W1964962870","https://openalex.org/W1973831620","https://openalex.org/W1978661986","https://openalex.org/W1980900887","https://openalex.org/W2034068348","https://openalex.org/W2096333253","https://openalex.org/W2136414484","https://openalex.org/W2296218809","https://openalex.org/W2408525833","https://openalex.org/W2561490710","https://openalex.org/W2604556510","https://openalex.org/W2604662548","https://openalex.org/W2731782677","https://openalex.org/W2737792314","https://openalex.org/W2892844106","https://openalex.org/W2954383399","https://openalex.org/W2961535796","https://openalex.org/W2962253150","https://openalex.org/W3015277054","https://openalex.org/W3042565597","https://openalex.org/W3136043138","https://openalex.org/W3137421143","https://openalex.org/W3176118284","https://openalex.org/W4220900977","https://openalex.org/W4394660363","https://openalex.org/W6601297327","https://openalex.org/W6628772041","https://openalex.org/W6635409236","https://openalex.org/W6674310493","https://openalex.org/W6730652076","https://openalex.org/W6765436296","https://openalex.org/W6796734896"],"related_works":["https://openalex.org/W2989932438","https://openalex.org/W2963373297","https://openalex.org/W843301618","https://openalex.org/W4294498805","https://openalex.org/W4287758182","https://openalex.org/W3208882810","https://openalex.org/W3099765033","https://openalex.org/W3201070945","https://openalex.org/W4210531038","https://openalex.org/W4294811585"],"abstract_inverted_index":{"From":[0],"a":[1,102],"practitioners":[2],"perspective,":[3],"the":[4,11,35,43,50,53,74,91,106,145],"number":[5],"of":[6,37,52,93],"in-put/output":[7],"examples":[8,25],"used":[9],"during":[10],"training":[12,39,94,107,119],"process":[13],"in":[14,22,115,144],"program":[15,76,146],"synthesis":[16,77,147],"studies":[17],"is":[18,121],"too":[19],"large,":[20],"as":[21,47,49],"practice,":[23],"these":[24],"must":[26],"be":[27],"labeled":[28],"by":[29,56],"hand.":[30],"Therefore,":[31],"this":[32],"paper":[33],"analyzes":[34],"influence":[36],"different":[38],"set":[40],"sizes":[41],"on":[42,69,109,118,128],"performance,":[44],"generalization":[45],"ability,":[46],"well":[48],"structure":[51],"programs":[54,125],"generated":[55],"grammar-guided":[57,137],"genetic":[58,138],"programming.":[59],"We":[60,96],"compare":[61],"down-sampled":[62,113,141],"lexicase":[63,67,85,100,142],"selection":[64,68,143],"with":[65,140],"standard":[66,99],"three":[70],"common":[71],"problems":[72],"from":[73],"general":[75],"benchmark":[78],"suite.":[79],"First,":[80],"we":[81,133],"find":[82,97],"that":[83,98],"both":[84],"variants":[86],"are":[87],"robust":[88],"against":[89],"reducing":[90],"amount":[92],"data.":[95],"has":[101],"tendency":[103],"to":[104,135],"overfit":[105],"data":[108,120],"some":[110],"problems.":[111],"With":[112],"lexicase,":[114],"contrast,":[116],"overfitting":[117],"reduced":[122],"and":[123],"evolved":[124],"generalize":[126],"better":[127],"held-out":[129],"test":[130],"cases.":[131],"Consequently,":[132],"suggest":[134],"use":[136],"programming":[139],"domain.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}