{"id":"https://openalex.org/W4415748113","doi":"https://doi.org/10.1109/tmc.2025.3627276","title":"Reinforcement Learning-Based Edge-Assisted Inference With Multimodal Data","display_name":"Reinforcement Learning-Based Edge-Assisted Inference With Multimodal Data","publication_year":2025,"publication_date":"2025-10-31","ids":{"openalex":"https://openalex.org/W4415748113","doi":"https://doi.org/10.1109/tmc.2025.3627276"},"language":null,"primary_location":{"id":"doi:10.1109/tmc.2025.3627276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3627276","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Mobile Computing","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":null,"display_name":"Yu Liu","orcid":"https://orcid.org/0009-0001-0367-2844"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Institute of Artificial Intelligence, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0001-0367-2844","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068976123","display_name":"Liang Xiao","orcid":"https://orcid.org/0000-0003-2402-611X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Xiao","raw_affiliation_strings":["Department of Informatics and Communication Engineering, Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","Department of Informatics and Communication Engineering, Xiamen University, China"],"raw_orcid":"https://orcid.org/0000-0003-2402-611X","affiliations":[{"raw_affiliation_string":"Department of Informatics and Communication Engineering, Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Department of Informatics and Communication Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102835792","display_name":"Chuxuan Wang","orcid":"https://orcid.org/0000-0002-3759-9542"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuxuan Wang","raw_affiliation_strings":["Institute of Artificial Intelligence, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004056315","display_name":"Zefang Lv","orcid":"https://orcid.org/0000-0003-3880-5069"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zefang Lv","raw_affiliation_strings":["Institute of Space Internet, Fudan University, Shanghai, China","School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3880-5069","affiliations":[{"raw_affiliation_string":"Institute of Space Internet, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113276397","display_name":"Yiwen Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Zhan","raw_affiliation_strings":["Department of Informatics and Communication Engineering, Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","Department of Informatics and Communication Engineering, Xiamen University, China"],"raw_orcid":"https://orcid.org/0009-0001-2089-6938","affiliations":[{"raw_affiliation_string":"Department of Informatics and Communication Engineering, Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Department of Informatics and Communication Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102921648","display_name":"Yilin Xiao","orcid":"https://orcid.org/0000-0002-0717-7488"},"institutions":[{"id":"https://openalex.org/I4210104064","display_name":"Shenzhen Academy of Robotics","ror":"https://ror.org/01h027j09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210104064"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Xiao","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China","Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0717-7488","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China","institution_ids":["https://openalex.org/I4210104064"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013729643","display_name":"Helin Yang","orcid":"https://orcid.org/0000-0001-9697-7470"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helin Yang","raw_affiliation_strings":["Department of Informatics and Communication Engineering, Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","Department of Informatics and Communication Engineering, Xiamen University, China"],"raw_orcid":"https://orcid.org/0000-0001-9697-7470","affiliations":[{"raw_affiliation_string":"Department of Informatics and Communication Engineering, Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Department of Informatics and Communication Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30572946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"4","first_page":"5016","last_page":"5031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.17900000512599945,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.17900000512599945,"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":0.1006999984383583,"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/T10860","display_name":"Speech and Audio Processing","score":0.08630000054836273,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8220999836921692},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.3986999988555908},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3982999920845032},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.35199999809265137},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.35190001130104065},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3440000116825104},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.32910001277923584},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3271999955177307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.82669997215271},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8220999836921692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5576000213623047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5385000109672546},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.3986999988555908},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.32910001277923584},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.27549999952316284},{"id":"https://openalex.org/C95167961","wikidata":"https://www.wikidata.org/wiki/Q4483495","display_name":"Fiducial inference","level":5,"score":0.27459999918937683},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C186108316","wikidata":"https://www.wikidata.org/wiki/Q352530","display_name":"Adaptive neuro fuzzy inference system","level":4,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2025.3627276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3627276","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7013925519","display_name":null,"funder_award_id":"62371408","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G70360640","display_name":null,"funder_award_id":"62301335","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7203450436","display_name":null,"funder_award_id":"U21A20444","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2014284812","https://openalex.org/W2108598243","https://openalex.org/W2169976759","https://openalex.org/W2194775991","https://openalex.org/W2468875367","https://openalex.org/W2605258629","https://openalex.org/W2619383789","https://openalex.org/W2890952074","https://openalex.org/W2897268228","https://openalex.org/W2981114133","https://openalex.org/W3016098309","https://openalex.org/W3047544015","https://openalex.org/W3049640275","https://openalex.org/W3059280052","https://openalex.org/W3088405768","https://openalex.org/W3156711202","https://openalex.org/W3168271366","https://openalex.org/W3174783634","https://openalex.org/W3202577926","https://openalex.org/W3209457805","https://openalex.org/W3211149853","https://openalex.org/W3214374352","https://openalex.org/W3214378007","https://openalex.org/W4282981352","https://openalex.org/W4283204791","https://openalex.org/W4285197124","https://openalex.org/W4285257856","https://openalex.org/W4285261368","https://openalex.org/W4290945178","https://openalex.org/W4293195477","https://openalex.org/W4294891997","https://openalex.org/W4313144683","https://openalex.org/W4320008754","https://openalex.org/W4385245566","https://openalex.org/W4385656539","https://openalex.org/W4386450026"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"extract":[4],"embeddings":[5],"from":[6,44],"multimodal":[7,25,79,89,114],"data":[8,221],"such":[9,27,135,171],"as":[10,28,130,132,136,152,172],"audio,":[11],"images,":[12],"and":[13,20,37,46,68,99,105,124,139,159,162,179,202,205,214,220],"LiDAR,":[14],"each":[15,109,128],"with":[16],"heterogeneous":[17],"computational":[18,183,191],"demands":[19],"representation":[21],"abilities":[22],"to":[23,49,54,112,148,185,234],"support":[24],"services":[26],"audio-visual":[29],"speech":[30],"recognition.":[31],"Reinforcement":[32],"learning":[33],"(RL)-based":[34],"model":[35,42,94,198],"selection":[36,95],"splitting":[38],"schemes":[39,229],"determine":[40],"the":[41,47,73,121,143,150,190,195,227],"variants":[43],"DNNs":[45,115],"components":[48],"offload":[50],"in":[51],"unimodal":[52],"models":[53],"reduce":[55],"inference":[56,64,90,141,157,163,174,177,210,231],"latency,":[57,178,211],"aiming":[58],"for":[59,108,209],"a":[60,153],"three-fold":[61],"trade-off":[62],"among":[63],"accuracy,":[65,175],"computation":[66],"cost,":[67],"communication":[69],"overhead":[70],"but":[71],"ignore":[72],"heterogeneity":[74],"of":[75,127,156,182,197],"different":[76],"modalities":[77],"within":[78],"DNNs.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84],"propose":[85],"an":[86],"RL-based":[87],"edge-assisted":[88,100],"scheme":[91],"that":[92,226],"optimizes":[93],"at":[96],"modality":[97],"level":[98],"policies,":[101],"including":[102],"collaborative":[103],"servers":[104],"partition":[106,203],"points":[107,204],"feature":[110],"extractor":[111],"perform":[113],"on":[116,120],"mobile":[117],"devices.":[118],"Based":[119],"information":[122],"complexity":[123,192],"historical":[125],"influence":[126],"modality,":[129],"well":[131],"real-time":[133],"observations":[134],"channel":[137],"gain,":[138],"previous":[140],"performance,":[142],"policy":[144,166],"distributions":[145],"are":[146],"designed":[147],"maximize":[149],"utility,":[151],"weighted":[154],"sum":[155],"latency":[158],"energy":[160,212],"consumption,":[161,213],"accuracy.":[164],"Safe":[165],"exploration":[167],"further":[168],"mitigates":[169],"risks":[170],"low":[173],"intolerable":[176],"improper":[180],"allocation":[181],"resources":[184],"specific":[186,217],"modalities.":[187],"We":[188],"analyze":[189],"affected":[193],"by":[194],"number":[196],"variants,":[199],"edge":[200],"servers,":[201],"derive":[206],"performance":[207,232],"bounds":[208],"utility":[215],"under":[216],"sample":[218],"sizes":[219],"rates.":[222],"Experimental":[223],"results":[224],"show":[225],"proposed":[228],"improve":[230],"compared":[233],"benchmark":[235],"schemes.":[236]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-31T00:00:00"}