{"id":"https://openalex.org/W7106734636","doi":"https://doi.org/10.48550/arxiv.2511.17668","title":"MedPEFT-CL: Dual-Phase Parameter-Efficient Continual Learning with Medical Semantic Adapter and Bidirectional Memory Consolidation","display_name":"MedPEFT-CL: Dual-Phase Parameter-Efficient Continual Learning with Medical Semantic Adapter and Bidirectional Memory Consolidation","publication_year":2025,"publication_date":"2025-11-21","ids":{"openalex":"https://openalex.org/W7106734636","doi":"https://doi.org/10.48550/arxiv.2511.17668"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2511.17668","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.17668","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2511.17668","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gao, Ziyuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gao, Ziyuan","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":false,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8507999777793884,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8507999777793884,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06790000200271606,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.032999999821186066,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.8026000261306763},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.6072999835014343},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.5570999979972839},{"id":"https://openalex.org/keywords/consolidation","display_name":"Consolidation (business)","score":0.33489999175071716},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.32260000705718994},{"id":"https://openalex.org/keywords/lifelong-learning","display_name":"Lifelong learning","score":0.3172000050544739}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.8026000261306763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656000256538391},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.5570999979972839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5260000228881836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3555000126361847},{"id":"https://openalex.org/C2776014549","wikidata":"https://www.wikidata.org/wiki/Q3050847","display_name":"Consolidation (business)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C108771440","wikidata":"https://www.wikidata.org/wiki/Q368475","display_name":"Lifelong learning","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2985722590","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medical knowledge","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C48455012","wikidata":"https://www.wikidata.org/wiki/Q2892593","display_name":"Memory consolidation","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.27970001101493835}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2511.17668","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.17668","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2511.17668","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.17668","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0],"vision-language":[1,42,197],"segmentation":[2],"models":[3],"suffer":[4],"from":[5,167],"catastrophic":[6,165],"forgetting":[7,166,179],"when":[8],"adapting":[9],"to":[10],"new":[11,60,117,141],"anatomical":[12],"structures,":[13],"requiring":[14],"complete":[15],"retraining":[16],"that":[17,54,82,122,136,149,163],"limits":[18],"their":[19],"clinical":[20],"deployment.":[21],"Although":[22],"continual":[23,35,51,193],"learning":[24,36,52,58,80,139,194],"approaches":[25,37],"have":[26],"been":[27],"studied":[28],"for":[29,40,91,192],"various":[30],"applications,":[31],"targeted":[32],"research":[33],"on":[34,72],"specifically":[38],"designed":[39],"medical":[41,92,142,169,175,196],"tasks":[43,61,93,118],"remains":[44],"underexplored.":[45],"We":[46],"propose":[47],"MedPEFT-CL,":[48],"a":[49,68,99,109,131,145],"parameter-efficient":[50,89],"framework":[53,190],"addresses":[55],"both":[56],"efficient":[57,138],"of":[59,64,140],"and":[62,88,98,158,181],"preservation":[63],"previous":[65,168],"knowledge":[66,100],"through":[67,94],"dual-phase":[69,75],"architecture":[70,76],"based":[71],"CLIPSeg.":[73],"Our":[74,126],"features":[77],"an":[78],"adaptive":[79],"phase":[81,102],"employs":[83],"semantic":[84],"similarity-based":[85],"adapter":[86,133],"allocation":[87,134],"fine-tuning":[90],"prompt":[95],"similarity":[96],"analysis,":[97],"consolidation":[101,112],"employing":[103],"bi-directional":[104],"Fisher-memory":[105,161],"coordination.":[106],"This":[107],"creates":[108],"reinforcing":[110],"cycle:":[111],"directs":[113],"replay":[114],"priorities":[115],"while":[116,154],"provide":[119],"challenging":[120],"samples":[121],"improve":[123],"retention":[124,183],"strategies.":[125],"key":[127],"contributions":[128],"are:":[129],"(1)":[130],"semantic-driven":[132],"mechanism":[135],"enables":[137],"tasks,":[143],"(2)":[144],"bi-modal":[146],"LoRA":[147],"adaptation":[148],"significantly":[150],"reduces":[151],"trainable":[152],"parameters":[153],"maintaining":[155],"cross-modal":[156],"learning,":[157],"(3)":[159],"bidirectional":[160],"coordination":[162],"prevents":[164],"tasks.":[170],"Extensive":[171],"experiments":[172],"across":[173],"diverse":[174],"datasets":[176],"demonstrate":[177],"superior":[178],"mitigation":[180],"performance":[182],"with":[184],"minimal":[185],"parameter":[186],"overhead,":[187],"making":[188],"the":[189],"effective":[191],"in":[195],"scenarios.":[198]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-11-27T00:00:00"}