{"id":"https://openalex.org/W3113997496","doi":"https://doi.org/10.1145/3430984.3430997","title":"Is it hard to learn a classifier on this dataset?","display_name":"Is it hard to learn a classifier on this dataset?","publication_year":2020,"publication_date":"2020-12-28","ids":{"openalex":"https://openalex.org/W3113997496","doi":"https://doi.org/10.1145/3430984.3430997","mag":"3113997496"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3430997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5012400928","display_name":"Sudarsun Santhiappan","orcid":"https://orcid.org/0000-0001-5769-2405"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"funder","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudarsun Santhiappan","raw_affiliation_strings":["Department of Computer Science and Engineering IIT Madras, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering IIT Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038082743","display_name":"Nitin Shravan","orcid":null},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nitin Shravan","raw_affiliation_strings":["Research and Development Division BUDDI.AI New York, USA"],"affiliations":[{"raw_affiliation_string":"Research and Development Division BUDDI.AI New York, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009374923","display_name":"Balaraman Ravindran","orcid":"https://orcid.org/0000-0002-5364-7639"},"institutions":[{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"funder","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Balaraman Ravindran","raw_affiliation_strings":["Robert Bosch Centre for Data Science and AI (RBC-DSAI) IIT Madras, India"],"affiliations":[{"raw_affiliation_string":"Robert Bosch Centre for Data Science and AI (RBC-DSAI) IIT Madras, India","institution_ids":["https://openalex.org/I4210151956","https://openalex.org/I24676775"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.118,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.441492,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":60,"max":69},"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"306"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9999,"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":0.9999,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9931,"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":0.993,"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/statistical-classification","display_name":"Statistical classification","score":0.42898312}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.78856933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75079066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.63823193},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.60931987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.56596744},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5328878},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.42898312},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41494122}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3430997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":22,"referenced_works":["https://openalex.org/W1569704244","https://openalex.org/W1963678392","https://openalex.org/W1987971958","https://openalex.org/W1990165991","https://openalex.org/W2003984511","https://openalex.org/W2029064186","https://openalex.org/W2047987854","https://openalex.org/W2051224630","https://openalex.org/W2102539288","https://openalex.org/W2125877832","https://openalex.org/W2135695572","https://openalex.org/W2618735189","https://openalex.org/W2750378047","https://openalex.org/W2810226251","https://openalex.org/W2897897876","https://openalex.org/W2945790622","https://openalex.org/W2973136425","https://openalex.org/W3088137798","https://openalex.org/W349912947","https://openalex.org/W4211131356","https://openalex.org/W4213009331","https://openalex.org/W43871266"],"related_works":["https://openalex.org/W4398756457","https://openalex.org/W4361733776","https://openalex.org/W4319005243","https://openalex.org/W4298130764","https://openalex.org/W4281776617","https://openalex.org/W4200459988","https://openalex.org/W3213683101","https://openalex.org/W3186233728","https://openalex.org/W3035095237","https://openalex.org/W3020897463"],"abstract_inverted_index":{"Identifying":[0],"how":[1],"hard":[2],"it":[3,132],"is":[4,123,144],"to":[5,41,133,138],"achieve":[6],"a":[7,12,37,51,60,73,83,106],"good":[8],"classification":[9,44,57,75,96,111],"performance":[10],"on":[11,63],"given":[13,84,121],"dataset":[14,29,38,61,85,122],"can":[15],"be":[16],"useful":[17],"in":[18],"data":[19],"analysis,":[20],"model":[21,68],"selection,":[22],"and":[23,89,110,130,149,154],"meta-learning.":[24],"We":[25,67,156],"hypothesize":[26],"that":[27],"the":[28,34,42,55,78,87,99,102,120,134,140],"clustering":[30,65,80,109,128],"indices":[31,81,129],"which":[32],"capture":[33],"characteristics":[35],"of":[36,59,82,108],"are":[39],"related":[40],"respective":[43],"complexity.":[45],"In":[46],"this":[47,69],"work,":[48],"we":[49,104,125],"propose":[50],"method":[52,159],"for":[53],"determining":[54],"empirical":[56],"complexity":[58,97,136],"based":[62],"its":[64,95,127],"indices.":[66],"mapping":[70],"problem":[71],"as":[72,98],"supervised":[74],"task":[76],"where":[77],"estimated":[79],"form":[86],"features":[88],"with":[90],"an":[91],"indicator":[92],"variable":[93],"representing":[94],"label.":[100],"For":[101],"experiments,":[103],"use":[105],"set":[107],"algorithms":[112],"spanning":[113],"different":[114],"modeling":[115],"assumptions.":[116],"To":[117],"test":[118],"whether":[119],"complex,":[124],"estimate":[126],"feed":[131],"trained":[135],"classifier":[137],"output":[139],"prediction.":[141],"Our":[142],"approach":[143],"simple,":[145],"but":[146],"very":[147],"effective":[148],"robust":[150],"across":[151],"many":[152],"datasets":[153],"classifiers.":[155],"evaluate":[157],"our":[158],"using":[160],"60":[161],"publicly":[162],"available":[163],"datasets.":[164]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3113997496","counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-03-22T15:41:21.793894","created_date":"2021-01-05"}