{"id":"https://openalex.org/W7128613629","doi":"https://doi.org/10.1109/icnsc66229.2025.00081","title":"IA-MOE: An Intensity-Aware Mixture of Experts for DNN Inference","display_name":"IA-MOE: An Intensity-Aware Mixture of Experts for DNN Inference","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W7128613629","doi":"https://doi.org/10.1109/icnsc66229.2025.00081"},"language":null,"primary_location":{"id":"doi:10.1109/icnsc66229.2025.00081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc66229.2025.00081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Networking, Sensing and Control (ICNSC)","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":"https://openalex.org/A5074898763","display_name":"Meiyan Zeng","orcid":"https://orcid.org/0000-0002-4203-5792"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Meiyan Zeng","raw_affiliation_strings":["University of Helsinki,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki,Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sasu Tarkoma","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sasu Tarkoma","raw_affiliation_strings":["University of Helsinki,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki,Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100386595","display_name":"Xiaoli Liu","orcid":"https://orcid.org/0000-0002-9815-6550"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xiaoli Liu","raw_affiliation_strings":["University of Helsinki,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki,Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.5135999917984009,"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":0.5135999917984009,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.07519999891519547,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.06210000067949295,"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/inference","display_name":"Inference","score":0.8547999858856201},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.42480000853538513},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4219000041484833},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42089998722076416},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.397599995136261},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3910999894142151},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3772999942302704},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.36570000648498535},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.3497999906539917}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8547999858856201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5742999911308289},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5051000118255615},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38029998540878296},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.3474999964237213},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C186108316","wikidata":"https://www.wikidata.org/wiki/Q352530","display_name":"Adaptive neuro fuzzy inference system","level":4,"score":0.32659998536109924},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C61455927","wikidata":"https://www.wikidata.org/wiki/Q1030529","display_name":"Blossom algorithm","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icnsc66229.2025.00081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc66229.2025.00081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Networking, Sensing and Control (ICNSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.879976749420166}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,33,43,71,99,176,181],"ever-increasing":[2],"parameter":[3],"scale":[4],"and":[5,23,29,64,77,111,168,187],"structural":[6],"complexity":[7,60],"of":[8,35,74,93],"deep":[9],"neural":[10],"network":[11],"(DNN)":[12],"models,":[13],"traditional":[14],"cloud-based":[15],"inference":[16,36,49,82,117,144,189,200],"encounters":[17,51],"bottlenecks":[18],"in":[19,61,124,146,190,201],"performance,":[20],"privacy":[21],"protection,":[22],"energy":[24,78,169],"efficiency.":[25],"While":[26],"edge":[27,30,39],"computing":[28,128,192],"intelligence":[31,203],"facilitate":[32],"migration":[34],"tasks":[37,110],"to":[38,42,57,66,179],"servers":[40],"closer":[41],"data":[44],"source,":[45],"existing":[46],"end-edge-cloud":[47],"collaborative":[48,188],"still":[50],"critical":[52],"challenges,":[53],"such":[54],"as":[55,103],"sensitivity":[56],"heterogeneous":[58],"resources,":[59],"multi-objective":[62],"optimization,":[63],"adaptability":[65],"dynamic":[67,81],"workloads.":[68],"To":[69,171],"achieve":[70],"joint":[72],"optimization":[73],"end-toend":[75],"latency":[76,167],"consumption":[79],"under":[80],"requests":[83],"with":[84],"multi-resource":[85],"constraints,":[86],"we":[87],"propose":[88],"IA-MoE,":[89],"an":[90,125,147],"intensity-aware":[91],"Mixture":[92],"Experts":[94],"(MoE)":[95],"framework.":[96],"By":[97],"modeling":[98],"model":[100],"partitioning":[101,186],"problem":[102,107],"a":[104,195],"bilateral":[105],"matching":[106],"between":[108],"layer":[109],"virtual":[112],"machine":[113],"resources":[114],"for":[115,165,184,198],"each":[116],"request,":[118],"IA-MoE":[119,132,156],"dynamically":[120],"partitions":[121],"DNN":[122,185],"models":[123],"edge-cloud":[126],"hybrid":[127,191],"environment.":[129,151],"We":[130],"evaluate":[131],"using":[133],"three":[134],"representative":[135],"DNNs":[136],"(i.e.,":[137],"AlexNet,":[138],"VGG16,":[139],"ResNet50)":[140],"on":[141],"two":[142],"public":[143],"datasets":[145],"enhanced":[148],"CloudSimSDN":[149],"simulation":[150],"Experiments":[152],"results":[153],"demonstrate":[154],"that":[155],"significantly":[157],"outperforms":[158],"baseline":[159],"methods":[160],"regarding":[161],"weighted":[162],"normalized":[163],"metrics":[164],"end-to-end":[166],"consumption.":[170],"our":[172],"knowledge,":[173],"this":[174],"is":[175],"first":[177],"study":[178],"introduce":[180],"MoE":[182],"paradigm":[183],"environments,":[193],"providing":[194],"practical":[196],"solution":[197],"efficient":[199],"artificial":[202],"applications.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-12T00:00:00"}