{"id":"https://openalex.org/W7138977405","doi":"https://doi.org/10.1145/3788149.3788245","title":"Dynamic Soft Data Pruning: Adaptive Selection and Scheduling for Data-Efficient Learning","display_name":"Dynamic Soft Data Pruning: Adaptive Selection and Scheduling for Data-Efficient Learning","publication_year":2025,"publication_date":"2025-12-12","ids":{"openalex":"https://openalex.org/W7138977405","doi":"https://doi.org/10.1145/3788149.3788245"},"language":null,"primary_location":{"id":"doi:10.1145/3788149.3788245","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788149.3788245","pdf_url":null,"source":null,"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 2025 9th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3788149.3788245","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Junda Yu","orcid":"https://orcid.org/0009-0008-1205-5275"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junda Yu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-1205-5275","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119426537","display_name":"Bangyin Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bangyin Xiang","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-4652-9637","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89733931,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.2849999964237213,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.2849999964237213,"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":0.20260000228881836,"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":0.06859999895095825,"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/scheduling","display_name":"Scheduling (production processes)","score":0.5224999785423279},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3671000003814697},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.3652999997138977},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.2831999957561493},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.2700999975204468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6837999820709229},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46219998598098755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3702999949455261},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C140073362","wikidata":"https://www.wikidata.org/wiki/Q738759","display_name":"Soft computing","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3788149.3788245","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788149.3788245","pdf_url":null,"source":null,"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 2025 9th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3788149.3788245","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788149.3788245","pdf_url":null,"source":null,"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 2025 9th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1997865285","https://openalex.org/W2108598243","https://openalex.org/W3113682753","https://openalex.org/W4386057733","https://openalex.org/W4386072234","https://openalex.org/W4402727870","https://openalex.org/W4402915941","https://openalex.org/W7133235177"],"related_works":[],"abstract_inverted_index":{"Training":[0],"deep":[1],"models":[2],"on":[3],"large-scale":[4],"datasets":[5,149],"is":[6],"often":[7],"inefficient":[8],"due":[9,48],"to":[10,35,49,86,130,160,165],"redundant":[11],"and":[12,24,52,126],"uninformative":[13],"samples.":[14,168],"Data":[15],"pruning":[16,54,76,106],"offers":[17],"a":[18,66,104],"solution":[19],"in":[20,44],"improving":[21],"training":[22,37,47,113,140,162],"efficiency":[23],"model":[25,46],"performance.":[26,144],"However,":[27],"most":[28],"existing":[29],"static":[30],"selection":[31],"methods":[32],"cannot":[33],"adapt":[34],"evolving":[36],"dynamics,":[38],"or":[39],"dynamic":[40,62],"approaches":[41],"may":[42],"result":[43],"suboptimal":[45],"cumulative":[50],"errors":[51],"fixed":[53],"ratios.":[55],"To":[56],"address":[57],"these":[58],"issues,":[59],"we":[60,79],"propose":[61],"soft":[63],"data":[64,110,141],"pruning,":[65],"principled":[67],"framework":[68],"that":[69,151],"ensures":[70],"optimization":[71],"while":[72],"adaptively":[73],"adjusting":[74],"the":[75,81,135],"ratio.":[77],"Specifically,":[78],"minimize":[80],"expected":[82],"squared":[83],"loss":[84,100],"error":[85],"derive":[87],"optimal":[88],"sample-level":[89],"retention":[90,116],"probabilities,":[91],"estimated":[92],"efficiently":[93],"via":[94],"an":[95],"exponential":[96],"moving":[97],"average":[98],"of":[99,138],"statistics.":[101],"In":[102],"addition,":[103],"U-shaped":[105],"schedule":[107],"dynamically":[108],"adapts":[109],"volume":[111],"with":[112,163],"progress:":[114],"high":[115],"early":[117],"for":[118,124],"robust":[119],"representation":[120],"learning,":[121],"reduced":[122,139],"mid-training":[123],"efficiency,":[125],"increased":[127],"near":[128],"convergence":[129],"prevent":[131],"overfitting.":[132],"Therefore,":[133],"using":[134],"same":[136],"amount":[137],"achieves":[142,154],"better":[143,155],"Experiment":[145],"results":[146],"across":[147],"different":[148],"demonstrate":[150],"our":[152],"method":[153],"results,":[156],"achieving":[157],"comparable":[158],"accuracy":[159],"full-data":[161],"up":[164],"50%":[166],"fewer":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-20T00:00:00"}