{"id":"https://openalex.org/W4410227418","doi":"https://doi.org/10.1109/wcnc61545.2025.10978329","title":"Learning-Based Low-Latency Collaborative Inference for Multi-Branch Models in D2D-Assisted MEC","display_name":"Learning-Based Low-Latency Collaborative Inference for Multi-Branch Models in D2D-Assisted MEC","publication_year":2025,"publication_date":"2025-03-24","ids":{"openalex":"https://openalex.org/W4410227418","doi":"https://doi.org/10.1109/wcnc61545.2025.10978329"},"language":"en","primary_location":{"id":"doi:10.1109/wcnc61545.2025.10978329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc61545.2025.10978329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Wireless Communications and Networking Conference (WCNC)","raw_type":"proceedings-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/A5063754038","display_name":"Kai Guo","orcid":"https://orcid.org/0000-0001-9699-7527"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Guo","raw_affiliation_strings":["Shenzhen Institute of Artificial Intelligence and Robotics for Society,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society,Shenzhen,China","institution_ids":["https://openalex.org/I4210104064"]}]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Xiao","raw_affiliation_strings":["Shenzhen Institute of Artificial Intelligence and Robotics for Society,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society,Shenzhen,China","institution_ids":["https://openalex.org/I4210104064"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091024726","display_name":"Xiaozhen Lu","orcid":"https://orcid.org/0000-0001-8247-0353"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaozhen Lu","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","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":["Xiamen University,Department of Information and Communication Engineering,Xiamen,China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Department of Information and Communication Engineering,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063754038"],"corresponding_institution_ids":["https://openalex.org/I4210104064"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10028508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"06"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9714999794960022,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9617000222206116,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7658923864364624},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6615422368049622},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6062617301940918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43389010429382324},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09619143605232239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7658923864364624},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6615422368049622},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6062617301940918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43389010429382324},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09619143605232239}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wcnc61545.2025.10978329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc61545.2025.10978329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Wireless Communications and Networking Conference (WCNC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2585908400","display_name":null,"funder_award_id":"62301335,62202222,U21A20444","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2193145675","https://openalex.org/W2341528187","https://openalex.org/W2618530766","https://openalex.org/W2916798096","https://openalex.org/W2980856918","https://openalex.org/W3083715619","https://openalex.org/W3088802706","https://openalex.org/W3127919686","https://openalex.org/W3153345798","https://openalex.org/W3196954395","https://openalex.org/W4200551577","https://openalex.org/W4236099117","https://openalex.org/W4293198317","https://openalex.org/W4317038519","https://openalex.org/W6637373629","https://openalex.org/W6741002519"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"Deploying":[0],"high-complexity":[1],"deep":[2],"neural":[3],"network":[4,71,110,159],"(DNN)":[5],"on":[6],"mobile":[7,35,123],"devices":[8,43,124,176],"presents":[9],"significant":[10],"challenges,":[11],"stemming":[12],"from":[13,66,156],"the":[14,22,59,92,100,103,108,113,126,144,157,161,174,181,187,191],"conflict":[15],"between":[16,102],"their":[17],"computationally":[18],"intensive":[19],"demands":[20],"and":[21,73,107,160],"constrained":[23],"computational":[24,74,114,145],"resources.":[25],"Device-to-device":[26],"(<tex":[27],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[28,32],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$D$</tex>":[29],"2":[30],"<tex":[31],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$D$</tex>)":[33],"assisted":[34],"edge":[36,127],"computing":[37],"(MEC)":[38],"exploits":[39],"sharing":[40],"resources":[41],"among":[42],"to":[44,98,121,142,153,172],"perform":[45],"DNN":[46,62,96,104],"inference":[47,56,85,192],"collaboratively":[48],"for":[49,87,129,177],"higher":[50],"efficiency.":[51],"However,":[52],"most":[53],"existing":[54],"collaborative":[55,84,175],"schemes":[57],"ignore":[58],"structure":[60],"of":[61,94,116],"models,":[63,89],"thus":[64],"suffering":[65],"high":[67],"latency":[68,193],"under":[69],"dynamic":[70],"conditions":[72],"loads.":[75],"In":[76,132],"this":[77],"paper,":[78],"we":[79,134],"propose":[80],"a":[81,150,169],"learning-based":[82],"low-latency":[83],"scheme":[86,189],"multi-branch":[88],"which":[90,148],"schedules":[91],"computations":[93],"each":[95,117,164],"layer":[97],"optimize":[99],"alignment":[101],"structure's":[105],"characteristics":[106],"D2D":[109,158],"environments.":[111],"Specifically,":[112],"task":[115],"branch":[118],"is":[119],"assigned":[120],"nearby":[122],"or":[125],"server":[128],"efficient":[130],"collaboration.":[131],"addition,":[133],"design":[135],"proximal":[136],"policy":[137],"optimization":[138],"with":[139,195],"task-specific":[140],"architecture":[141],"choose":[143],"scheduling":[146],"policy,":[147],"contains":[149],"two-stream":[151],"NN":[152],"extract":[154],"features":[155],"tasks":[162,179],"at":[163],"layer,":[165],"as":[166,168],"well":[167],"multi-head":[170],"output":[171],"obtain":[173],"all":[178],"in":[180],"layer.":[182],"Simulation":[183],"results":[184],"show":[185],"that":[186],"proposed":[188],"reduces":[190],"compared":[194],"benchmarks.":[196]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}