{"id":"https://openalex.org/W4416143513","doi":"https://doi.org/10.1145/3746252.3760971","title":"Towards Equitable Coreset Selection: Addressing Challenges Under Class Imbalance","display_name":"Towards Equitable Coreset Selection: Addressing Challenges Under Class Imbalance","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416143513","doi":"https://doi.org/10.1145/3746252.3760971"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3760971","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3760971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","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/A5120346536","display_name":"Liyana Sahir Kallooriyakath","orcid":"https://orcid.org/0009-0008-9106-3715"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liyana Sahir Kallooriyakath","raw_affiliation_strings":["AI Garage, Mastercard, Gurugram, India"],"raw_orcid":"https://orcid.org/0009-0008-9106-3715","affiliations":[{"raw_affiliation_string":"AI Garage, Mastercard, Gurugram, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065264082","display_name":"Anugu Namratha Reddy","orcid":"https://orcid.org/0009-0002-3135-7291"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anugu Namratha Reddy","raw_affiliation_strings":["AI Garage, Mastercard, Gurugram, India"],"raw_orcid":"https://orcid.org/0009-0002-3135-7291","affiliations":[{"raw_affiliation_string":"AI Garage, Mastercard, Gurugram, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120443522","display_name":"B Srinath Achary","orcid":"https://orcid.org/0009-0006-5656-2899"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B Srinath Achary","raw_affiliation_strings":["AI Garage, Mastercard, Gurugram, India"],"raw_orcid":"https://orcid.org/0009-0006-5656-2899","affiliations":[{"raw_affiliation_string":"AI Garage, Mastercard, Gurugram, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089614841","display_name":"Ashutosh Sharma","orcid":"https://orcid.org/0009-0001-2594-7861"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashutosh Sharma","raw_affiliation_strings":["AI Garage, Mastercard, Gurugram, India"],"raw_orcid":"https://orcid.org/0009-0001-2594-7861","affiliations":[{"raw_affiliation_string":"AI Garage, Mastercard, Gurugram, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Krisha Shah","orcid":"https://orcid.org/0009-0003-4219-0527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krisha Shah","raw_affiliation_strings":["AI Garage, Mastercard, Gurugram, India"],"raw_orcid":"https://orcid.org/0009-0003-4219-0527","affiliations":[{"raw_affiliation_string":"AI Garage, Mastercard, Gurugram, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054341033","display_name":"Sonia Gupta","orcid":"https://orcid.org/0000-0001-6143-8653"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sonia Gupta","raw_affiliation_strings":["AI Garage, Mastercard, Gurugram, India"],"raw_orcid":"https://orcid.org/0000-0001-6143-8653","affiliations":[{"raw_affiliation_string":"AI Garage, Mastercard, Gurugram, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076286184","display_name":"Siddhartha Asthana","orcid":"https://orcid.org/0000-0002-6798-1240"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siddhartha Asthana","raw_affiliation_strings":["AI Garage, Mastercard, Gurugram, India"],"raw_orcid":"https://orcid.org/0000-0002-6798-1240","affiliations":[{"raw_affiliation_string":"AI Garage, Mastercard, Gurugram, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5120346536"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17504396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5181","last_page":"5185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.8388000130653381,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.8388000130653381,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0272000003606081,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.019700000062584877,"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/pruning","display_name":"Pruning","score":0.6200000047683716},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5752999782562256},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5457000136375427},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4909000098705292},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.32179999351501465}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6200000047683716},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5752999782562256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5526000261306763},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5457000136375427},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4909000098705292},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.4616999924182892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3571999967098236},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.33629998564720154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C45555294","wikidata":"https://www.wikidata.org/wiki/Q28113351","display_name":"Inequality","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3760971","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3760971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W3211082594","https://openalex.org/W4224952733"],"related_works":[],"abstract_inverted_index":{"Coreset":[0,36],"selection":[1,66],"reduces":[2],"training":[3],"cost":[4],"by":[5],"constructing":[6],"compact,":[7],"representative":[8],"subsets,":[9],"but":[10],"existing":[11],"methods":[12],"largely":[13],"assume":[14],"balanced":[15],"class":[16,61],"distributions.":[17],"Under":[18],"imbalance,":[19],"this":[20],"assumption":[21],"yields":[22],"biased":[23],"subsets":[24],"that":[25,52,76],"discard":[26],"critical":[27],"minority":[28,54],"samples":[29],"and":[30,63,80],"degrade":[31],"accuracy.":[32],"We":[33],"propose":[34],"Equitable":[35],"Selection":[37],"(ECS),":[38],"a":[39],"framework":[40],"tailored":[41],"for":[42,67],"imbalanced":[43,73],"data.":[44],"ECS":[45,77],"mitigates":[46],"these":[47],"issues":[48],"through":[49],"adaptive":[50],"pruning":[51],"preserves":[53],"examples,":[55],"class-sensitive":[56],"partitioning":[57],"aligned":[58],"with":[59],"skewed":[60],"distributions,":[62],"stratified":[64],"graph-cut":[65],"diverse":[68],"sampling.":[69],"Experiments":[70],"across":[71],"multiple":[72],"datasets":[74],"show":[75],"improves":[78],"generalization":[79],"substantially":[81],"boosts":[82],"minority-class":[83],"accuracy":[84],"compared":[85],"to":[86],"standard":[87],"coreset":[88],"methods.":[89]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-11-11T00:00:00"}