{"id":"https://openalex.org/W4415593989","doi":"https://doi.org/10.1109/jiot.2025.3625275","title":"CacheMoE: Task-Aware Expert Model Caching for Multitask Inference in Distributed Edge IoT Networks","display_name":"CacheMoE: Task-Aware Expert Model Caching for Multitask Inference in Distributed Edge IoT Networks","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415593989","doi":"https://doi.org/10.1109/jiot.2025.3625275"},"language":null,"primary_location":{"id":"doi:10.1109/jiot.2025.3625275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3625275","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"},"type":"article","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":"https://openalex.org/A5114666834","display_name":"Afsana Kabir Sinthia","orcid":"https://orcid.org/0009-0000-6066-6865"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Afsana Kabir Sinthia","raw_affiliation_strings":["Department of Artificial Intelligence, School of Computing, Kyung Hee University, Yongin, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-6066-6865","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, School of Computing, Kyung Hee University, Yongin, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077409827","display_name":"Nosin Ibna Mahbub","orcid":"https://orcid.org/0000-0002-0858-5563"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nosin Ibna Mahbub","raw_affiliation_strings":["Department of Artificial Intelligence, School of Computing, Kyung Hee University, Yongin, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-0858-5563","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, School of Computing, Kyung Hee University, Yongin, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013661291","display_name":"Nahid Sultan","orcid":"https://orcid.org/0000-0003-2953-7314"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Md Nahid Sultan","raw_affiliation_strings":["Department of Computer Science and Engineering, School of Computing, Kyung Hee University, Yongin, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-2953-7314","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, School of Computing, Kyung Hee University, Yongin, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000263913","display_name":"Eui\u2010Nam Huh","orcid":"https://orcid.org/0000-0003-0184-6975"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eui-Nam Huh","raw_affiliation_strings":["Department of Computer Science and Engineering, School of Computing, Kyung Hee University, Yongin, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0184-6975","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, School of Computing, Kyung Hee University, Yongin, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35928602"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25801173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"24","first_page":"55725","last_page":"55741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9923999905586243,"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"}},"topics":[{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9923999905586243,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9883000254631042,"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":0.9648000001907349,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6686999797821045},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.6025000214576721},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5776000022888184},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.52920001745224},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4973999857902527},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.48739999532699585},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43560001254081726},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4237000048160553},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4230000078678131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8840000033378601},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6686999797821045},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.6025000214576721},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.52920001745224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5253000259399414},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4821000099182129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4514000117778778},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3659000098705292},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C2781041963","wikidata":"https://www.wikidata.org/wiki/Q18348618","display_name":"Computation offloading","level":4,"score":0.3296000063419342},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.29899999499320984},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2025.3625275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3625275","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2565419328","https://openalex.org/W2624186268","https://openalex.org/W2809290718","https://openalex.org/W2916236867","https://openalex.org/W2963877604","https://openalex.org/W2964247799","https://openalex.org/W2968028544","https://openalex.org/W2987116703","https://openalex.org/W2987229805","https://openalex.org/W3002844053","https://openalex.org/W3017518089","https://openalex.org/W3023749864","https://openalex.org/W3023809615","https://openalex.org/W3047040155","https://openalex.org/W3085046840","https://openalex.org/W3096609285","https://openalex.org/W3122091261","https://openalex.org/W3122350435","https://openalex.org/W3125638814","https://openalex.org/W3132444044","https://openalex.org/W3136022984","https://openalex.org/W3138516171","https://openalex.org/W3161618639","https://openalex.org/W4205108433","https://openalex.org/W4206683212","https://openalex.org/W4210713758","https://openalex.org/W4220800818","https://openalex.org/W4285225730","https://openalex.org/W4293795158","https://openalex.org/W4309223941","https://openalex.org/W4315783855","https://openalex.org/W4321636555","https://openalex.org/W4323262593","https://openalex.org/W4362544381","https://openalex.org/W4381744661","https://openalex.org/W4389162698","https://openalex.org/W4391248691","https://openalex.org/W4392693694","https://openalex.org/W4393058305","https://openalex.org/W4393641009","https://openalex.org/W4394994461","https://openalex.org/W4398188181","https://openalex.org/W4401753387","https://openalex.org/W4401878796","https://openalex.org/W4402704566","https://openalex.org/W4408352822","https://openalex.org/W4410226386","https://openalex.org/W4410491899","https://openalex.org/W4413104867","https://openalex.org/W4413318953"],"related_works":[],"abstract_inverted_index":{"Multi-task":[0],"learning":[1],"(MTL)":[2],"has":[3],"emerged":[4],"as":[5,40],"the":[6,15,150,186,220],"preferred":[7],"strategy":[8],"for":[9,74,96,125,173],"integrating":[10],"artificial":[11],"intelligence":[12],"(AI)":[13],"into":[14,142],"Internet":[16],"of":[17],"Things":[18],"(IoT)":[19],"environments":[20],"by":[21,84],"enabling":[22],"a":[23,81,119,134,179,193],"single":[24],"model":[25,78,102,122],"to":[26,49,107,138,167,200],"perform":[27],"multiple":[28],"related":[29],"tasks":[30],"through":[31],"shared":[32],"representations.":[33],"Yet,":[34],"deploying":[35],"large-scale":[36],"MTL":[37,97,140],"models":[38,88,141,172],"such":[39],"vision":[41],"transformers":[42],"on":[43,185],"resource-constrained":[44],"devices":[45],"remains":[46],"challenging":[47],"due":[48],"their":[50],"high":[51],"computational":[52],"and":[53,68,110,147,181,210,227],"memory":[54],"demands.":[55],"While":[56],"edge-cloud":[57],"collaboration":[58],"offers":[59,80],"partial":[60],"relief":[61],"via":[62],"task":[63,188],"offloading,":[64],"it":[65],"introduces":[66],"latency":[67,211],"cloud":[69],"reliance,":[70],"which":[71],"are":[72,104],"incompatible":[73],"delay-sensitive":[75],"applications.":[76],"Edge":[77],"caching":[79,93,123,204],"promising":[82],"alternative":[83],"storing":[85],"frequently":[86],"used":[87],"locally.":[89],"However,":[90],"traditional":[91],"full-model":[92],"is":[94,165],"suboptimal":[95],"scenarios":[98],"where":[99],"only":[100],"task-specific":[101,144],"components":[103,146],"utilized,":[105],"leading":[106],"unnecessary":[108],"storage":[109,209],"computation":[111],"overhead.":[112],"To":[113],"address":[114],"this,":[115],"we":[116,190],"propose":[117],"CacheMoE,":[118],"task-aware":[120],"expert":[121,145,170,203],"framework":[124],"multi-task":[126,231],"inference":[127,232],"in":[128,178],"distributed":[129],"edge":[130,155,235],"environments.":[131,236],"CacheMoE":[132,217],"leverages":[133],"Mixture-of-Experts":[135],"(MoE)":[136],"architecture":[137],"decompose":[139],"modular,":[143],"selectively":[148],"caches":[149],"most":[151],"relevant":[152],"experts":[153],"across":[154,206,233],"nodes":[156],"(ENs).":[157],"A":[158],"Dynamic":[159],"Weighted":[160],"Federated":[161],"Learning":[162,197],"(DWFL)":[163],"algorithm":[164,199],"employed":[166],"train":[168],"personalized":[169],"popularity":[171],"each":[174],"user":[175],"equipment":[176],"(UE)":[177],"privacy-preserving":[180],"communication-efficient":[182],"manner.":[183],"Based":[184],"predicted":[187],"demands,":[189],"further":[191],"design":[192],"Multi-Agent":[194],"Deep":[195],"Reinforcement":[196],"(MADRL)":[198],"collaboratively":[201],"determine":[202],"decisions":[205],"ENs":[207],"under":[208],"constraints.":[212],"Experimental":[213],"results":[214],"demonstrate":[215],"that":[216],"significantly":[218],"improves":[219],"cache":[221],"hit":[222],"ratio,":[223],"reduces":[224],"cost,":[225],"latency,":[226],"supports":[228],"scalable,":[229],"low-latency":[230],"heterogeneous":[234]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-28T00:00:00"}