{"id":"https://openalex.org/W7166815095","doi":"https://doi.org/10.18653/v1/2026.findings-acl.608","title":"RADS: Reinforcement Learning-Based Sample Selection Improves Transfer Learning in Low-resource and Imbalanced Clinical Settings","display_name":"RADS: Reinforcement Learning-Based Sample Selection Improves Transfer Learning in Low-resource and Imbalanced Clinical Settings","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166815095","doi":"https://doi.org/10.18653/v1/2026.findings-acl.608"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.608","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.608","pdf_url":"https://aclanthology.org/2026.findings-acl.608.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.608.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139775110","display_name":"Wei Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139803437","display_name":"David Martinez Iraola","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Martinez Iraola","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070192389","display_name":"Anna Khanina","orcid":"https://orcid.org/0000-0003-2988-1676"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anna Khanina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023819089","display_name":"Lawrence Cavedon","orcid":"https://orcid.org/0000-0001-7464-857X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lawrence Cavedon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139785517","display_name":"Karin Verspoor","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karin Verspoor","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80481966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12501","last_page":"12516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.39089998602867126,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.39089998602867126,"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":0.15369999408721924,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.05270000174641609,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5109000205993652},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4772000014781952},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.46939998865127563},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.45350000262260437},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3361999988555908},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.31839999556541443}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116999983787537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5306000113487244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5232999920845032},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.608","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.608","pdf_url":"https://aclanthology.org/2026.findings-acl.608.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.608","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.608","pdf_url":"https://aclanthology.org/2026.findings-acl.608.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166815095.pdf","grobid_xml":"https://content.openalex.org/works/W7166815095.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"A":[0],"common":[1],"strategy":[2,70,92],"in":[3,54],"transfer":[4],"learning":[5,25,73],"is":[6,13,109],"few":[7],"shot":[8],"fine-tuning,":[9],"but":[10],"its":[11],"success":[12],"highly":[14],"dependent":[15],"on":[16,82,111],"the":[17,77],"quality":[18],"of":[19],"samples":[20],"selected":[21],"as":[22,28],"training":[23],"examples.Active":[24],"methods":[26],"such":[27],"uncertainty":[29],"sampling":[30,33],"and":[31,41],"diversity":[32],"can":[34],"select":[35],"useful":[36],"samples.However,":[37],"under":[38,100],"extremely":[39],"low-resource":[40],"classimbalanced":[42],"conditions,":[43],"they":[44],"often":[45],"favor":[46],"outliers":[47],"rather":[48],"than":[49],"truly":[50],"informative":[51,79],"samples,":[52],"resulting":[53],"degraded":[55],"performance.In":[56],"this":[57],"paper,":[58],"we":[59],"introduce":[60],"RADS":[61],"(Reinforcement":[62],"Adaptive":[63],"Domain":[64],"Sampling),":[65],"a":[66],"robust":[67,98],"sample":[68,90],"selection":[69,91],"using":[71],"reinforcement":[72],"(RL)":[74],"to":[75,105],"identify":[76],"most":[78],"samples.Experimental":[80],"evaluations":[81],"several":[83],"real":[84],"world":[85],"clinical":[86],"datasets":[87],"show":[88],"our":[89],"enhances":[93],"model":[94],"transferability":[95],"while":[96],"maintaining":[97],"performance":[99],"extreme":[101],"class":[102],"imbalance":[103],"compared":[104],"traditional":[106],"methods.Our":[107],"code":[108],"open-sourced":[110],"GitHub":[112],"1":[113],".":[114]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}