{"id":"https://openalex.org/W7168280342","doi":"https://doi.org/10.1109/icc59461.2026.11586972","title":"Unsupervised Out-of-Distribution Sample Selection for Reliable ML in Wireless Systems","display_name":"Unsupervised Out-of-Distribution Sample Selection for Reliable ML in Wireless Systems","publication_year":2026,"publication_date":"2026-05-24","ids":{"openalex":"https://openalex.org/W7168280342","doi":"https://doi.org/10.1109/icc59461.2026.11586972"},"language":"en","primary_location":{"id":"doi:10.1109/icc59461.2026.11586972","doi":"https://doi.org/10.1109/icc59461.2026.11586972","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icc59461.2026.11586972","pdf_url":null,"source":{"id":"https://openalex.org/S4306419201","display_name":"International Conference on Communications","issn_l":"1550-3607","issn":["1550-3607"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2026 - IEEE International Conference on Communications","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/icc59461.2026.11586972","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032701288","display_name":"Chinenye Tassie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chinenye Tassie","raw_affiliation_strings":["University of Texas at Austin,Wireless Networking & Communications Group,Austin,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Wireless Networking & Communications Group,Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080991767","display_name":"Abhinav Mahadevan","orcid":"https://orcid.org/0009-0005-5013-1652","observed_orcids":["https://orcid.org/0009-0005-5013-1652"]},"institutions":[{"id":"https://openalex.org/I4210115805","display_name":"Keysight Technologies (United States)","ror":"https://ror.org/02903cd17","country_code":"US","type":"company","lineage":["https://openalex.org/I4210115805"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Mahadevan","raw_affiliation_strings":["Software & AI Labs, Keysight Technologies,Santa Rosa,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software & AI Labs, Keysight Technologies,Santa Rosa,CA,USA","institution_ids":["https://openalex.org/I4210115805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080483470","display_name":"Kaushik Roy Chowdhury","orcid":"https://orcid.org/0000-0002-3570-2622","observed_orcids":["https://orcid.org/0000-0002-3570-2622"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik R. Chowdhury","raw_affiliation_strings":["University of Texas at Austin,Wireless Networking & Communications Group,Austin,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Wireless Networking & Communications Group,Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.5228999853134155,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.5228999853134155,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.27880001068115234,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.025200000032782555,"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/out-of-distribution-detection","display_name":"out-of-distribution detection","score":0.9959999918937683},{"id":"https://openalex.org/keywords/channel-state-information-compression","display_name":"channel state information compression","score":0.8259999752044678},{"id":"https://openalex.org/keywords/density-based-clustering","display_name":"density-based clustering","score":0.800000011920929},{"id":"https://openalex.org/keywords/csi-reconstruction","display_name":"CSI reconstruction","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6162999868392944},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4309000074863434},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2754000127315521},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc59461.2026.11586972","doi":"https://doi.org/10.1109/icc59461.2026.11586972","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icc59461.2026.11586972","pdf_url":null,"source":{"id":"https://openalex.org/S4306419201","display_name":"International Conference on Communications","issn_l":"1550-3607","issn":["1550-3607"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2026 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/icc59461.2026.11586972","doi":"https://doi.org/10.1109/icc59461.2026.11586972","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icc59461.2026.11586972","pdf_url":null,"source":{"id":"https://openalex.org/S4306419201","display_name":"International Conference on Communications","issn_l":"1550-3607","issn":["1550-3607"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2026 - IEEE International Conference on Communications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2734408173","https://openalex.org/W2962883549","https://openalex.org/W3200006281","https://openalex.org/W4401357445","https://openalex.org/W4408951793","https://openalex.org/W4413967661","https://openalex.org/W7082644038"],"related_works":["https://openalex.org/W3088353320","https://openalex.org/W7220925993","https://openalex.org/W6949272992","https://openalex.org/W4403407815","https://openalex.org/W7167250775","https://openalex.org/W7220817970","https://openalex.org/W7151757299","https://openalex.org/W7166515536","https://openalex.org/W7133236141","https://openalex.org/W7167939727"],"abstract_inverted_index":{"Incorporating":[0],"Machine":[1],"Learning":[2],"(ML)":[3],"approaches":[4],"within":[5],"wireless":[6,85,234],"systems":[7],"hinges":[8],"on":[9,66,139],"their":[10],"ability":[11],"to":[12,27,48,100,120,178,192,201],"handle":[13],"real-world":[14],"variability.":[15],"In":[16,172],"practice,":[17],"data":[18],"will":[19],"inevitably":[20],"deviate":[21],"from":[22,155,220],"the":[23,67,95,148,156,168,221,228,237],"training":[24],"distribution":[25],"due":[26],"new":[28],"devices,":[29],"changing":[30],"environments,":[31],"and":[32,63,124,159,194],"unforeseen":[33],"interference.":[34],"Out-of-Distribution":[35],"(OOD)":[36],"detection":[37,61,92,116,176,189],"provides":[38],"a":[39,58,109,179,210],"safeguard":[40],"by":[41,93,152],"identifying":[42],"these":[43,133],"shifts":[44],"before":[45],"they":[46],"lead":[47],"unreliable":[49],"model":[50],"behavior.":[51],"To":[52],"address":[53],"this":[54],"challenge,":[55],"we":[56,88,146],"develop":[57],"multi-stage":[59],"OOD":[60,91,115,136,150,230],"algorithm":[62],"evaluate":[64],"it":[65,191,200],"publicly":[68],"available":[69],"3GPP":[70],"NR":[71],"CSI":[72],"Compression":[73],"dataset,":[74],"which":[75],"contains":[76],"high-dimensional":[77],"Channel":[78],"State":[79],"Information":[80],"(CSI)":[81],"representative":[82],"of":[83,97,141],"realistic":[84,233],"propagation.":[86],"First,":[87],"perform":[89],"coarse":[90,175],"measuring":[94],"distance":[96],"incoming":[98],"samples":[99,151,216,231],"in-distribution":[101],"class":[102],"centers,":[103],"flagging":[104],"those":[105],"that":[106,128,164,227],"lie":[107],"beyond":[108],"threshold.":[110],"We":[111],"then":[112],"apply":[113],"fine":[114,188],"using":[117],"density-based":[118],"clustering":[119],"filter":[121],"spurious":[122],"anomalies":[123],"isolate":[125],"dense":[126],"clusters":[127],"representing":[129],"meaningful":[130],"shifts.":[131],"While":[132,203],"stages":[134],"identify":[135],"samples,":[137],"retraining":[138,165],"all":[140],"them":[142],"is":[143,205],"inefficient.":[144],"Instead,":[145],"rank":[147],"selected":[149],"discriminativeness":[153],"(distance":[154],"ID":[157],"distribution)":[158],"diversity":[160],"(feature":[161],"dissimilarity),":[162],"ensuring":[163],"incorporates":[166],"only":[167],"most":[169],"informative":[170],"examples.":[171],"our":[173],"analysis,":[174],"led":[177],"6.93%":[180],"increase":[181,225],"in":[182,244],"reconstruction":[183,212],"Mean":[184],"Squared":[185],"Error":[186],"(MSE),":[187],"raised":[190],"37.6%,":[193],"incorporating":[195],"discriminativeness\u2013diversity":[196],"ranking":[197],"further":[198],"increased":[199],"45.5%.":[202],"MSE":[204],"typically":[206],"minimized":[207],"during":[208],"training,":[209],"higher":[211],"error":[213],"for":[214,240],"detected":[215,229],"indicates":[217],"stronger":[218],"deviation":[219],"learned":[222],"manifold.":[223],"This":[224],"confirms":[226],"reflect":[232],"variations,":[235],"reinforcing":[236],"framework\u2019s":[238],"value":[239],"reliable":[241],"ML":[242],"deployment":[243],"dynamic":[245],"environments.":[246]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-07-15T00:00:00"}