{"id":"https://openalex.org/W4404569745","doi":"https://doi.org/10.48550/arxiv.2411.10385","title":"Low-Latency Task-Oriented Communications with Multi-Round, Multi-Task\n Deep Learning","display_name":"Low-Latency Task-Oriented Communications with Multi-Round, Multi-Task\n Deep Learning","publication_year":2024,"publication_date":"2024-11-15","ids":{"openalex":"https://openalex.org/W4404569745","doi":"https://doi.org/10.48550/arxiv.2411.10385"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.10385","pdf_url":"http://arxiv.org/pdf/2411.10385","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2411.10385","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089570143","display_name":"Yalin E. Sagduyu","orcid":"https://orcid.org/0000-0003-1576-5527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sagduyu, Yalin E.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024995674","display_name":"Tugba Erpek","orcid":"https://orcid.org/0000-0003-0168-2587"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erpek, Tugba","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039328157","display_name":"Aylin Yener","orcid":"https://orcid.org/0000-0003-0820-3390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yener, Aylin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021132487","display_name":"\u015eennur Uluku\u015f","orcid":"https://orcid.org/0000-0002-8219-8190"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ulukus, Sennur","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"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":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":78},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9714,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9714,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13731","display_name":"Advanced Computing and Algorithms","score":0.9309,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6838766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.63601494},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5566444},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.50958323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33906338},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32815593},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2387025},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12443176},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.045338213}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.10385","pdf_url":"http://arxiv.org/pdf/2411.10385","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.10385","pdf_url":"http://arxiv.org/pdf/2411.10385","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4360585206","https://openalex.org/W4323565446","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W4213079790","https://openalex.org/W3215138031","https://openalex.org/W3082895349","https://openalex.org/W3009238340","https://openalex.org/W2731899572","https://openalex.org/W2248239756"],"abstract_inverted_index":{"In":[0],"this":[1,91],"paper,":[2],"we":[3,93],"address":[4],"task-oriented":[5,268],"(or":[6],"goal-oriented)":[7],"communications":[8],"where":[9],"an":[10,115],"encoder":[11],"at":[12],"the":[13,30,42,51,74,79,86,102,122,126,129,132,135,143,150,177,180,200,203,216,243,265],"transmitter":[14,112],"learns":[15],"compressed":[16],"latent":[17],"representations":[18],"of":[19,81,105,118,165,179,207,210,221,227,267],"data,":[20],"which":[21],"are":[22,54],"then":[23],"transmitted":[24],"over":[25,121],"a":[26,32,35,95,138,172,238],"wireless":[27],"channel.":[28],"At":[29],"receiver,":[31,130],"decoder":[33],"performs":[34],"machine":[36],"learning":[37,98,157],"task,":[38],"specifically":[39],"for":[40,101,256],"classifying":[41],"received":[43],"signals.":[44],"The":[45,111],"deep":[46],"neural":[47,247],"networks":[48],"corresponding":[49],"to":[50,68,141,158,189,219],"encoder-decoder":[52],"pair":[53],"jointly":[55,159],"trained,":[56],"taking":[57],"both":[58,199],"channel":[59,82,106,123,166,192,208,228,254],"and":[60,131,202,250,252,272],"data":[61],"characteristics":[62],"into":[63],"account.":[64],"Our":[65],"objective":[66],"is":[67],"achieve":[69],"high":[70],"accuracy":[71,161,201,217,271],"in":[72,108,182,194],"completing":[73],"underlying":[75],"task":[76,144,183],"while":[77],"minimizing":[78],"number":[80,117,164,206],"uses":[83,107,193],"determined":[84],"by":[85,234],"encoder's":[87],"output":[88],"size.":[89],"To":[90],"end,":[92],"propose":[94],"multi-round,":[96],"multi-task":[97,156],"(MRMTL)":[99],"approach":[100,154],"dynamic":[103],"update":[104],"multi-round":[109],"transmissions.":[110],"incrementally":[113],"sends":[114],"increasing":[116],"encoded":[119],"samples":[120],"based":[124],"on":[125,187],"feedback":[127],"from":[128,137,237],"receiver":[133,181],"utilizes":[134],"signals":[136,236],"previous":[139],"round":[140],"enhance":[142],"performance,":[145],"rather":[146],"than":[147],"only":[148],"considering":[149],"latest":[151],"transmission.":[152],"This":[153],"employs":[155],"optimize":[160],"across":[162],"varying":[163],"uses,":[167,229],"treating":[168],"each":[169],"configuration":[170],"as":[171],"distinct":[173],"task.":[174],"By":[175],"evaluating":[176],"confidence":[178],"decisions,":[184],"MRMTL":[185,262],"decides":[186],"whether":[188],"allocate":[190],"additional":[191],"multiple":[195],"rounds.":[196],"We":[197,241,259],"characterize":[198],"delay":[204,233],"(total":[205],"uses)":[209],"MRMTL,":[211],"demonstrating":[212],"that":[213,220,261],"it":[214],"achieves":[215],"close":[218],"conventional":[222],"methods":[223],"requiring":[224],"large":[225],"numbers":[226],"but":[230],"with":[231],"reduced":[232],"incorporating":[235],"prior":[239],"round.":[240],"consider":[242],"CIFAR-10":[244],"dataset,":[245],"convolutional":[246],"network":[248],"architectures,":[249],"AWGN":[251],"Rayleigh":[253],"models":[255],"performance":[257],"evaluation.":[258],"show":[260],"significantly":[263],"improves":[264],"efficiency":[266],"communications,":[269],"balancing":[270],"latency":[273],"effectively.":[274]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4404569745","counts_by_year":[],"updated_date":"2025-04-11T23:43:07.706258","created_date":"2024-11-21"}