{"id":"https://openalex.org/W7138967451","doi":"https://doi.org/10.48550/arxiv.2603.15939","title":"Data-Local Autonomous LLM-Guided Neural Architecture Search for Multiclass Multimodal Time-Series Classification","display_name":"Data-Local Autonomous LLM-Guided Neural Architecture Search for Multiclass Multimodal Time-Series Classification","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7138967451","doi":"https://doi.org/10.48550/arxiv.2603.15939"},"language":"en","primary_location":{"id":"pmh:oai:eprints.soton.ac.uk:510767","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.15939","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021601776","display_name":"Emil Hardarson","orcid":"https://orcid.org/0000-0002-9497-4265"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hardarson, Emil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036550460","display_name":"Luka Biedebach","orcid":"https://orcid.org/0000-0003-0974-202X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biedebach, Luka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129773722","display_name":"\u00d3mar Bessi \u00d3marsson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u00d3marsson, \u00d3mar Bessi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129897111","display_name":"Teitur Hr\u00f3lfsson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hr\u00f3lfsson, Teitur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129852638","display_name":"Anna Sigridur Islind","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Islind, Anna Sigridur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089062610","display_name":"Mar\u00eda \u00d3skarsd\u00f3ttir","orcid":"https://orcid.org/0000-0001-5095-5356"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u00d3skarsd\u00f3ttir, Mar\u00eda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.47510001063346863,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.47510001063346863,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T13702","display_name":"Machine Learning in Healthcare","score":0.22339999675750732,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.16040000319480896,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5462999939918518},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5392000079154968},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5126000046730042},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44519999623298645},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.44269999861717224},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4320000112056732},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4108999967575073},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4004000127315521},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3977000117301941},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.39340001344680786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882000207901001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.660099983215332},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5690000057220459},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5392000079154968},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3393000066280365},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:eprints.soton.ac.uk:510767","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"},{"id":"doi:10.48550/arxiv.2603.15939","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15939","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.15939","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15939","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Applying":[0],"machine":[1],"learning":[2,48,150],"to":[3,25,89],"sensitive":[4,244],"time-series":[5,182],"data":[6,245],"is":[7,33,55,206],"often":[8,23],"bottlenecked":[9],"by":[10,237],"the":[11,202,209],"iteration":[12],"loop:":[13],"Performance":[14],"depends":[15],"strongly":[16],"on":[17,50,176],"preprocessing":[18],"and":[19,39,68,113,133,157,163,169,185,196,208],"architecture,":[20],"yet":[21],"training":[22,112],"has":[24],"run":[26],"on-premise":[27],"under":[28,116],"strict":[29],"data-local":[30],"constraints.":[31],"This":[32,53],"a":[34,44,98,117,159],"common":[35],"problem":[36],"in":[37,58],"healthcare":[38],"other":[40],"privacy-constrained":[41],"domains":[42],"(e.g.,":[43],"hospital":[45],"developing":[46],"deep":[47],"models":[49,219],"patient":[51],"EEG).":[52],"bottleneck":[54],"particularly":[56],"challenging":[57],"multimodal":[59,149],"fusion,":[60],"where":[61],"sensor":[62],"modalities":[63,191],"must":[64],"be":[65,94],"individually":[66],"preprocessed":[67],"then":[69],"combined.":[70],"LLM-guided":[71,101,210],"neural":[72],"architecture":[73,240],"search":[74,102,165,241],"(NAS)":[75],"can":[76],"automate":[77],"this":[78],"exploration,":[79],"but":[80],"most":[81,226],"existing":[82],"workflows":[83],"assume":[84],"cloud":[85],"execution":[86],"or":[87,141],"access":[88],"data-derived":[90],"artifacts":[91],"that":[92,104,201,220],"cannot":[93],"exposed.":[95],"We":[96,172],"present":[97],"novel":[99],"data-local,":[100],"framework":[103,146],"handles":[105],"candidate":[106],"pipelines":[107],"remotely":[108],"while":[109,242],"executing":[110],"all":[111],"evaluation":[114],"locally":[115],"fixed":[118],"protocol.":[119],"The":[120,198],"controller":[121],"observes":[122],"only":[123],"trial-level":[124],"summaries,":[125],"such":[126,192],"as":[127,193],"pipeline":[128],"descriptors,":[129],"metrics,":[130],"learning-curve":[131],"statistics,":[132],"failure":[134],"logs,":[135],"without":[136],"ever":[137],"accessing":[138],"raw":[139],"samples":[140],"intermediate":[142],"feature":[143],"representations.":[144],"Our":[145],"targets":[147],"multiclass,":[148],"via":[151],"one-vs-rest":[152],"binary":[153],"experts":[154],"per":[155],"class":[156],"modality,":[158],"lightweight":[160],"fusion":[161],"MLP,":[162],"joint":[164],"over":[166],"expert":[167],"architectures":[168],"modality-specific":[170],"preprocessing.":[171],"evaluate":[173],"our":[174,216,232],"method":[175,217,233],"two":[177],"regimes:":[178],"UEA30":[179],"(public":[180],"multivariate":[181],"classification":[183],"dataset)":[184],"SleepEDFx":[186],"sleep":[187],"staging":[188],"(heterogeneous":[189],"clinical":[190],"EEG,":[194],"EOG,":[195],"EMG).":[197],"results":[199],"show":[200],"modular":[203],"baseline":[204],"model":[205],"strong,":[207],"NAS":[211],"further":[212],"improves":[213],"it.":[214],"Notably,":[215],"finds":[218],"perform":[221],"within":[222],"published":[223],"ranges":[224],"across":[225],"benchmark":[227],"datasets.":[228],"Across":[229],"both":[230],"settings,":[231],"reduces":[234],"manual":[235],"intervention":[236],"enabling":[238],"unattended":[239],"keeping":[243],"on-premise.":[246]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-20T00:00:00"}