{"id":"https://openalex.org/W4414539481","doi":"https://doi.org/10.1109/icc52391.2025.11161290","title":"A Plug-and-Play Module for Enhancing Fault-Tolerant Distributed Inference Based on Gaussian Dropout","display_name":"A Plug-and-Play Module for Enhancing Fault-Tolerant Distributed Inference Based on Gaussian Dropout","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4414539481","doi":"https://doi.org/10.1109/icc52391.2025.11161290"},"language":"en","primary_location":{"id":"doi:10.1109/icc52391.2025.11161290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhangcheng Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhangcheng Hou","raw_affiliation_strings":["Keio University,Department of Information and Computer Science,Yokohama,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,Department of Information and Computer Science,Yokohama,Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016337773","display_name":"Tomoaki Ohtsuki","orcid":"https://orcid.org/0000-0003-3961-1426"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoaki Ohtsuki","raw_affiliation_strings":["Keio University,Department of Information and Computer Science,Yokohama,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,Department of Information and Computer Science,Yokohama,Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I203951103"],"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":"4553","last_page":"4558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.9592999815940857,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9466000199317932,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/lossy-compression","display_name":"Lossy compression","score":0.7928000092506409},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7781999707221985},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6337000131607056},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5909000039100647},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5009999871253967},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.48739999532699585},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.42179998755455017},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40630000829696655}],"concepts":[{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.7928000092506409},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7781999707221985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724399983882904},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6337000131607056},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5909000039100647},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44620001316070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.42179998755455017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40950000286102295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3822000026702881},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C54108766","wikidata":"https://www.wikidata.org/wiki/Q391064","display_name":"Packet loss","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C2776157432","wikidata":"https://www.wikidata.org/wiki/Q1375683","display_name":"Normality","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc52391.2025.11161290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2808976322","https://openalex.org/W2896180420","https://openalex.org/W2960833983","https://openalex.org/W2963037989","https://openalex.org/W2969236120","https://openalex.org/W3014798366","https://openalex.org/W3043914740","https://openalex.org/W3167490029","https://openalex.org/W3182501581","https://openalex.org/W4205369066","https://openalex.org/W4205999233","https://openalex.org/W4210839873","https://openalex.org/W4226206247","https://openalex.org/W4283204791","https://openalex.org/W4283214771","https://openalex.org/W4295872615"],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"deep":[1],"neural":[2],"network":[3,62],"(DNN)":[4],"models":[5,142],"to":[6,81,98,125],"the":[7,37,53,77,93,100,103,135,137],"Internet":[8],"of":[9,39,55,79,102,140],"Things":[10],"(IoT)":[11],"for":[12,22],"distributed":[13],"inference":[14,40,84,138],"(DI)":[15],"is":[16,74,122,146],"becoming":[17],"an":[18],"increasingly":[19],"common":[20],"requirement":[21],"AI":[23],"applications.":[24],"When":[25],"IoT":[26,145],"transmissions":[27],"occur":[28],"over":[29],"lossy":[30,58,144],"networks,":[31],"data":[32],"loss":[33],"can":[34,51],"significantly":[35,147],"affect":[36],"accuracy":[38,54,139],"tasks.":[41],"Therefore,":[42],"we":[43,65,91,111],"propose":[44],"a":[45,67,118],"plug-and-play":[46,119],"module":[47],"called":[48],"Loss-Adapter,":[49,136],"which":[50],"improve":[52],"DI":[56],"on":[57,86,143],"networks.":[59],"To":[60,107],"simulate":[61],"packet":[63],"loss,":[64],"design":[66],"Gaussian":[68,104],"distribution":[69],"sampling":[70],"dropout.":[71],"This":[72],"idea":[73],"utilized":[75],"during":[76],"training":[78],"Loss-Adapter":[80],"acquire":[82],"fault-tolerant":[83],"capability":[85],"unreliable":[87],"communication":[88],"links.":[89],"Moreover,":[90],"use":[92],"Tree-structured":[94],"Parzen":[95],"Estimator":[96],"algorithm":[97],"optimize":[99],"parameters":[101],"dropout":[105],"layer.":[106],"avoiding":[108],"catastrophic":[109],"forgetting,":[110],"implement":[112],"freeze":[113],"training.":[114],"In":[115],"addition,":[116],"as":[117],"module,":[120],"it":[121],"very":[123],"easy":[124],"train":[126],"and":[127],"use.":[128],"Our":[129],"experiments":[130],"show":[131],"that":[132],"by":[133],"applying":[134],"DNN":[141],"improved.":[148]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}