{"id":"https://openalex.org/W4399454950","doi":"https://doi.org/10.48550/arxiv.2406.03944","title":"Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples","display_name":"Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples","publication_year":2024,"publication_date":"2024-06-06","ids":{"openalex":"https://openalex.org/W4399454950","doi":"https://doi.org/10.48550/arxiv.2406.03944"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.03944","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.03944","pdf_url":"https://arxiv.org/pdf/2406.03944","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.03944","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073047048","display_name":"Dake Bu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bu, Dake","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080467417","display_name":"Wei Huang","orcid":"https://orcid.org/0000-0003-3009-4741"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078812767","display_name":"Taiji Suzuki","orcid":"https://orcid.org/0000-0003-3459-1016"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suzuki, Taiji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100995802","display_name":"Cheng Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000546219","display_name":"Qingfu Zhang","orcid":"https://orcid.org/0000-0003-0786-0671"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qingfu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101799658","display_name":"Zhiqiang Xu","orcid":"https://orcid.org/0000-0002-5693-8933"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zhiqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014196059","display_name":"Hau\u2212San Wong","orcid":"https://orcid.org/0000-0002-1530-7529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wong, Hau-San","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9922000169754028,"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/T10320","display_name":"Neural Networks and Applications","score":0.9922000169754028,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9782999753952026,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.5180864334106445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5094595551490784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45831578969955444},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3833369314670563}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5180864334106445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5094595551490784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45831578969955444},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3833369314670563}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.03944","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.03944","pdf_url":"https://arxiv.org/pdf/2406.03944","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.03944","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.03944","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.03944","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.03944","pdf_url":"https://arxiv.org/pdf/2406.03944","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1361243275","display_name":"Towards an Explainable, Efficient, and Reliable Federated Learning Framework: A Solution for Data Heterogeneity","funder_award_id":"24K20848","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2207295377","display_name":"\u5927\u898f\u6a21\u57fa\u76e4\u30e2\u30c7\u30eb\u306e\u9769\u65b0\u7684\u539f\u7406\u89e3\u660e\u3068\u65b9\u6cd5\u8ad6\u306e\u65b0\u5c55\u958b","funder_award_id":"24K02905","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7053381585","display_name":null,"funder_award_id":"JPMJCR2015","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G7939374355","display_name":null,"funder_award_id":"JPMJCR2115","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399454950.pdf","grobid_xml":"https://content.openalex.org/works/W4399454950.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Neural":[0],"Network-based":[1],"active":[2],"learning":[3,80,160,170],"(NAL)":[4],"is":[5,142],"a":[6,20,66,78,85,152,162,177,183],"cost-effective":[7],"data":[8,87],"selection":[9],"technique":[10],"that":[11,111,131,138],"utilizes":[12],"neural":[13],"networks":[14],"to":[15,59,120,128,145,167,176],"select":[16],"and":[17,48,97,114,122],"train":[18],"on":[19],"small":[21,148,153],"subset":[22],"of":[23,38,45,72,171],"samples.":[24],"While":[25],"existing":[26],"work":[27],"successfully":[28],"develops":[29],"various":[30],"effective":[31],"or":[32,91],"theory-justified":[33],"NAL":[34,76,116],"algorithms,":[35],"the":[36,39,70,105,123,143,157,168],"understanding":[37],"two":[40],"commonly":[41],"used":[42],"query":[43,74],"criteria":[44],"NAL:":[46],"uncertainty-based":[47,113],"diversity-based,":[49],"remains":[50],"in":[51,104],"its":[52],"infancy.":[53],"In":[54],"this":[55,139],"work,":[56],"we":[57,83],"try":[58],"move":[60],"one":[61,121],"step":[62],"forward":[63],"by":[64,95],"offering":[65],"unified":[67],"explanation":[68],"for":[69,182],"success":[71],"both":[73,112],"criteria-based":[75],"from":[77],"feature":[79],"view.":[81],"Specifically,":[82],"consider":[84],"feature-noise":[86],"model":[88],"comprising":[89],"easy-to-learn":[90],"hard-to-learn":[92],"features":[93],"disrupted":[94],"noise,":[96],"conduct":[98],"analysis":[99],"over":[100],"2-layer":[101],"NN-based":[102],"NALs":[103],"pool-based":[106],"scenario.":[107],"We":[108,135],"provably":[109],"show":[110],"diversity-based":[115],"are":[117],"inherently":[118],"amenable":[119],"same":[124],"principle,":[125],"i.e.,":[126],"striving":[127],"prioritize":[129],"samples":[130],"contain":[132],"yet-to-be-learned":[133,172],"features.":[134],"further":[136],"prove":[137],"shared":[140],"principle":[141],"key":[144],"their":[146],"success-achieve":[147],"test":[149,164,185],"error":[150,165,186],"within":[151],"labeled":[154],"set.":[155],"Contrastingly,":[156],"strategy-free":[158],"passive":[159],"exhibits":[161],"large":[163],"due":[166],"inadequate":[169],"features,":[173],"necessitating":[174],"resort":[175],"significantly":[178],"larger":[179],"label":[180],"complexity":[181],"sufficient":[184],"reduction.":[187],"Experimental":[188],"results":[189],"validate":[190],"our":[191],"findings.":[192]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}