{"id":"https://openalex.org/W7167891428","doi":"https://doi.org/10.1145/3795095.3805130","title":"ROIDS: Robust Outlier-Aware Informed Down-Sampling","display_name":"ROIDS: Robust Outlier-Aware Informed Down-Sampling","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167891428","doi":"https://doi.org/10.1145/3795095.3805130"},"language":null,"primary_location":{"id":"doi:10.1145/3795095.3805130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3795095.3805130","pdf_url":null,"source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3795095.3805130","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004342649","display_name":"Alina Geiger","orcid":"https://orcid.org/0009-0002-3413-283X"},"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":"Alina Geiger","raw_affiliation_strings":["Johannes Gutenberg University Mainz, Mainz, Germany"],"raw_orcid":"https://orcid.org/0009-0002-3413-283X","affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049752195","display_name":"Martin Briesch","orcid":"https://orcid.org/0000-0002-8209-1465"},"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":"Martin Briesch","raw_affiliation_strings":["Johannes Gutenberg University Mainz, Mainz, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8209-1465","affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"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/I62318514","display_name":"University of Duisburg-Essen","ror":"https://ror.org/04mz5ra38","country_code":"DE","type":"education","lineage":["https://openalex.org/I62318514"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Sobania","raw_affiliation_strings":["University of Duisburg-Essen, Essen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8873-7143","affiliations":[{"raw_affiliation_string":"University of Duisburg-Essen, Essen, Germany","institution_ids":["https://openalex.org/I62318514"]}]},{"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, Mainz, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3376-427X","affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.94446218,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"762","last_page":"770"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.40549999475479126,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.40549999475479126,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.21250000596046448,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.05000000074505806,"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/overfitting","display_name":"Overfitting","score":0.8776999711990356},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8295999765396118},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.8154000043869019},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4797999858856201},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4505000114440918},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.44530001282691956},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.36800000071525574},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.36480000615119934}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8776999711990356},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8295999765396118},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.8154000043869019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6389999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5834000110626221},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5673999786376953},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5252000093460083},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.359499990940094},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C70259352","wikidata":"https://www.wikidata.org/wiki/Q1847839","display_name":"Robust regression","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3795095.3805130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3795095.3805130","pdf_url":null,"source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3795095.3805130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3795095.3805130","pdf_url":null,"source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W164607750","https://openalex.org/W1969885422","https://openalex.org/W2029469881","https://openalex.org/W2034068348","https://openalex.org/W2054536516","https://openalex.org/W2061011797","https://openalex.org/W2072473332","https://openalex.org/W2122646361","https://openalex.org/W2604767342","https://openalex.org/W2789595241","https://openalex.org/W2798474464","https://openalex.org/W2888571299","https://openalex.org/W2961535796","https://openalex.org/W2983029853","https://openalex.org/W2997591727","https://openalex.org/W3037244434","https://openalex.org/W3042565597","https://openalex.org/W4254182148","https://openalex.org/W4366339690","https://openalex.org/W4384024946","https://openalex.org/W4385189557","https://openalex.org/W4385189965","https://openalex.org/W4395093981","https://openalex.org/W4409674065"],"related_works":[],"abstract_inverted_index":{"Informed":[0,70],"down-sampling":[1,182],"(IDS)":[2],"is":[3,39,85,108],"known":[4],"to":[5,60,87,95,98,159],"improve":[6],"performance":[7,38],"in":[8,50,111,114,186,195],"symbolic":[9,187],"regression":[10],"when":[11,190],"combined":[12],"with":[13,133],"various":[14],"selection":[15,185],"strategies,":[16],"especially":[17,189],"tournament":[18],"selection.":[19],"However,":[20],"recent":[21],"work":[22],"found":[23],"that":[24,36,58],"IDS's":[25],"gains":[26],"are":[27],"not":[28],"consistent":[29],"across":[30,170],"all":[31,122,160,171],"problems.":[32,106,125,156,174],"Our":[33],"analysis":[34],"reveals":[35],"IDS":[37,45,92,129,148],"worse":[40],"for":[41,184],"problems":[42,132],"containing":[43],"outliers.":[44,61],"systematically":[46],"favors":[47],"including":[48],"outliers":[49,75,96,135,191],"subsets":[51],"which":[52,72,115],"pushes":[53],"GP":[54],"towards":[55],"finding":[56],"solutions":[57],"overfit":[59],"To":[62],"address":[63],"this,":[64],"we":[65],"introduce":[66],"ROIDS":[67,83,116,126,164,179],"(Robust":[68],"Outlier-Aware":[69],"Down-Sampling),":[71],"excludes":[73],"potential":[74],"from":[76],"the":[77,89,118,153,166,196],"sampling":[78],"process":[79],"of":[80,91,104,143,152],"IDS.":[81],"With":[82],"it":[84],"possible":[86],"keep":[88],"advantages":[90],"without":[93],"overfitting":[94],"and":[97],"compete":[99],"on":[100,121,130,139,149],"a":[101,140,180],"wide":[102,141],"range":[103,142],"benchmark":[105,124,155,173],"This":[107,175],"also":[109],"reflected":[110],"our":[112],"experiments":[113],"shows":[117],"desired":[119],"behavior":[120,177],"studied":[123,161],"consistently":[127],"outperforms":[128],"synthetic":[131],"added":[134],"as":[136,138],"well":[137],"complex":[144],"real-world":[145,154],"problems,":[146],"surpassing":[147],"over":[150],"80%":[151],"Moreover,":[157],"compared":[158],"baseline":[162],"approaches,":[163],"achieves":[165],"best":[167],"average":[168],"rank":[169],"tested":[172],"robust":[176],"makes":[178],"reliable":[181],"method":[183],"regression,":[188],"may":[192],"be":[193],"included":[194],"data":[197],"set.":[198]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-11T00:00:00"}