{"id":"https://openalex.org/W7137819555","doi":"https://doi.org/10.1609/aaai.v40i17.38473","title":"Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection","display_name":"Diffusion Reconstruction-based Data Likelihood Estimation for Core-Set Selection","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137819555","doi":"https://doi.org/10.1609/aaai.v40i17.38473"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i17.38473","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i17.38473","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38473/42435","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38473/42435","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129668926","display_name":"Mingyang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Mingyang Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou)\nHong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou)\nHong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678238","display_name":"Jiawei Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161496","display_name":"A*STAR Graduate Academy","ror":"https://ror.org/059yjzn93","country_code":"SG","type":"education","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210161496"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiawei Du","raw_affiliation_strings":["CFAR, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"CFAR, A*STAR, Singapore","institution_ids":["https://openalex.org/I4210161496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129648655","display_name":"Bo Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bo Huang","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou)\nHong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou)\nHong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694574","display_name":"Yi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Dongguan University of Technology"],"affiliations":[{"raw_affiliation_string":"Dongguan University of Technology","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129745835","display_name":"Xiaobo Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Zhang","raw_affiliation_strings":["Southwest Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129667449","display_name":"Wei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou)\nHong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou)\nHong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129668926"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03422619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"17","first_page":"14556","last_page":"14564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6588000059127808,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6588000059127808,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.03020000085234642,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.029100000858306885,"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/heuristic","display_name":"Heuristic","score":0.5839999914169312},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5680000185966492},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.5238000154495239},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3540000021457672},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.3490000069141388},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3353999853134155},{"id":"https://openalex.org/keywords/standard-deviation","display_name":"Standard deviation","score":0.33149999380111694},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.32580000162124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6269999742507935},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5839999914169312},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5680000185966492},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46560001373291016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4569000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453900009393692},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34290000796318054},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2809000015258789},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i17.38473","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i17.38473","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38473/42435","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i17.38473","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i17.38473","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38473/42435","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2291908008","display_name":null,"funder_award_id":"2023A03J0013","funder_id":"https://openalex.org/F4320335480","funder_display_name":"Guangzhou Municipal Science and Technology Project"},{"id":"https://openalex.org/G5957623925","display_name":null,"funder_award_id":"2023B151","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6719889613","display_name":null,"funder_award_id":"2023B1515120058","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G7020882947","display_name":null,"funder_award_id":"2023A03J0003","funder_id":"https://openalex.org/F4320335480","funder_display_name":"Guangzhou Municipal Science and Technology Project"},{"id":"https://openalex.org/G8142099083","display_name":null,"funder_award_id":"2023A03J0003","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G8835817537","display_name":null,"funder_award_id":"2023A03J0013","funder_id":"https://openalex.org/F4320323537","funder_display_name":"Hong Kong University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335480","display_name":"Guangzhou Municipal Science and Technology Project","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137819555.pdf","grobid_xml":"https://content.openalex.org/works/W7137819555.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"core-set":[1],"selection":[2,145],"methods":[3],"predominantly":[4],"rely":[5],"on":[6,129,176],"heuristic":[7],"scoring":[8,96,138],"signals":[9],"such":[10],"as":[11],"training":[12,151],"dynamics":[13],"or":[14],"model":[15,40,184],"uncertainty,":[16],"lacking":[17],"explicit":[18],"modeling":[19],"of":[20,87,123,155,165],"data":[21,58,78,99,125,172,180],"likelihood.":[22,126],"This":[23],"omission":[24],"may":[25],"hinder":[26],"the":[27,82,110,116,156,162,177],"constructed":[28],"subset":[29],"from":[30],"capturing":[31],"subtle":[32],"yet":[33],"critical":[34],"distributional":[35,181],"structures":[36],"that":[37,52,115,132,161],"underpin":[38],"effective":[39,137],"training.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,69,102],"propose":[46],"a":[47,71,93,119],"novel,":[48],"theoretically":[49],"grounded":[50,80],"approach":[51],"leverages":[53],"diffusion":[54,89],"models":[55],"to":[56,108],"estimate":[57],"likelihood":[59],"via":[60],"reconstruction":[61,75,112,133],"deviation":[62,117,134],"induced":[63],"by":[64],"partial":[65],"reverse":[66],"denoising.":[67],"Specifically,":[68],"establish":[70],"formal":[72],"connection":[73],"between":[74,179],"error":[76],"and":[77,147,183],"likelihood,":[79],"in":[81,171],"Evidence":[83],"Lower":[84],"Bound":[85],"(ELBO)":[86],"Markovian":[88],"processes,":[90],"thereby":[91],"enabling":[92],"principled,":[94],"distribution-aware":[95],"criterion":[97],"for":[98],"selection.":[100],"Complementarily,":[101],"introduce":[103],"an":[104,136],"efficient":[105],"information-theoretic":[106],"method":[107],"identify":[109],"optimal":[111],"timestep,":[113],"ensuring":[114],"provides":[118],"reliable":[120],"signal":[121],"indicative":[122],"underlying":[124],"Extensive":[127],"experiments":[128],"ImageNet":[130],"demonstrate":[131],"offers":[135],"criterion,":[139],"consistently":[140],"outperforming":[141],"existing":[142],"baselines":[143],"across":[144],"ratios,":[146],"closely":[148],"matching":[149],"full-data":[150],"using":[152],"only":[153],"50%":[154],"data.":[157],"Further":[158],"analysis":[159],"shows":[160],"likelihood-informed":[163],"nature":[164],"our":[166],"score":[167],"reveals":[168],"informative":[169],"insights":[170],"selection,":[173],"shedding":[174],"light":[175],"interplay":[178],"characteristics":[182],"learning":[185],"preferences.":[186]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}