{"id":"https://openalex.org/W7160288810","doi":"https://doi.org/10.1109/ton.2026.3689748","title":"Toward Energy-Efficient Collaborative Inference and Fine-Tuning: Matching Model Compression and Offloading With Resource Availability","display_name":"Toward Energy-Efficient Collaborative Inference and Fine-Tuning: Matching Model Compression and Offloading With Resource Availability","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160288810","doi":"https://doi.org/10.1109/ton.2026.3689748"},"language":null,"primary_location":{"id":"doi:10.1109/ton.2026.3689748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ton.2026.3689748","pdf_url":null,"source":{"id":"https://openalex.org/S5407042750","display_name":"IEEE Transactions on Networking","issn_l":"2998-4157","issn":["2998-4157"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Networking","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/A5135327242","display_name":"Yue-e Zhou","orcid":"https://orcid.org/0000-0001-7655-4884"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuee Zhou","raw_affiliation_strings":["Software College, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0001-7655-4884","affiliations":[{"raw_affiliation_string":"Software College, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135336111","display_name":"Lianbo Ma","orcid":"https://orcid.org/0000-0002-9969-211X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianbo Ma","raw_affiliation_strings":["Software College, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-9969-211X","affiliations":[{"raw_affiliation_string":"Software College, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135376089","display_name":"Xingwei Wang","orcid":"https://orcid.org/0000-0003-2856-4716"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwei Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0003-2856-4716","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135363530","display_name":"Qing Li","orcid":"https://orcid.org/0000-0002-6071-473X"},"institutions":[{"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":"Qing Li","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-6071-473X","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135348389","display_name":"Carla Fabiana Chiasserini","orcid":"https://orcid.org/0000-0003-1410-660X"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Carla Fabiana Chiasserini","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1410-660X","affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135403632","display_name":"Guangjie Han","orcid":"https://orcid.org/0000-0002-6921-7369"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangjie Han","raw_affiliation_strings":["Department of Information Science and Engineering, Hohai University, Changzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6921-7369","affiliations":[{"raw_affiliation_string":"Department of Information Science and Engineering, Hohai University, Changzhou, China","institution_ids":["https://openalex.org/I163340411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5135327242"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83433308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"5127","last_page":"5142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.8866000175476074,"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":0.8866000175476074,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.01979999989271164,"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/T14347","display_name":"Big Data and Digital Economy","score":0.007600000128149986,"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/inference","display_name":"Inference","score":0.6980000138282776},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5615000128746033},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.45590001344680786},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.44020000100135803},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43880000710487366},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.39149999618530273},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.388700008392334},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.3750999867916107},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3695000112056732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082000017166138},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6980000138282776},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5615000128746033},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4323999881744385},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3418999910354614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32280001044273376},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ton.2026.3689748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ton.2026.3689748","pdf_url":null,"source":{"id":"https://openalex.org/S5407042750","display_name":"IEEE Transactions on Networking","issn_l":"2998-4157","issn":["2998-4157"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Networking","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5549115538597107,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G3603513928","display_name":null,"funder_award_id":"62472079","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,206],"consider":[1],"the":[2,69,73,91,95,132,144,148,153,179,194,203,211],"collaborative":[3,126],"inference":[4,59,127],"acceleration":[5],"task":[6],"via":[7],"cloud-edge-end":[8],"collaboration,":[9],"which":[10,88],"involves":[11],"a":[12,120,173,182,188],"series":[13],"of":[14,93,146,152,198],"tightly":[15,109],"coupled":[16,110],"decision-making":[17],"steps,":[18],"including":[19],"<italic":[20,28,35,42],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[21,29,36,43],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">which</i>":[22],"DNN":[23,133],"model":[24,70,116],"to":[25,32,38,45,157,177,192],"be":[26],"selected,":[27],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">how":[30],"much</i>":[31],"compress":[33],"model,":[34,40,134],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">how</i>":[37],"partition":[39,137],"and":[41,58,61,76,128,139,159,187,229],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">where</i>":[44],"offload":[46],"partitioned":[47],"submodels.":[48],"In":[49,112],"practical":[50],"deployments,":[51],"these":[52,108],"decisions":[53],"jointly":[54,63,124],"affect":[55],"both":[56,226],"fine-tuning":[57,129],"performance,":[60],"must":[62],"account":[64],"for":[65,107],"such":[66,103],"aspects":[67],"as":[68,83,85,119],"being":[71],"used,":[72],"computational":[74,140],"resources":[75],"local":[77],"datasets":[78],"available":[79],"at":[80],"each":[81],"device,":[82],"well":[84],"network":[86],"latencies,":[87],"significantly":[89],"increases":[90],"complexity":[92],"optimizing":[94,125],"problem.":[96],"Yet,":[97],"no":[98],"existing":[99],"studies":[100],"focus":[101],"on":[102],"joint":[104],"optimization":[105,122],"problem":[106,118],"decisions.":[111],"this":[113,117,163],"paper,":[114],"we":[115,165],"multi-dimensional":[121],"problem,":[123],"by":[130],"selecting":[131],"compression":[135],"level,":[136],"strategy,":[138,186],"resource":[141],"allocation,":[142],"with":[143,214],"objective":[145],"minimizing":[147],"overall":[149],"energy":[150,227],"consumption":[151],"learning-inference":[154],"process,":[155,181],"subject":[156],"accuracy":[158,204],"latency":[160],"constraints.":[161],"To":[162],"end,":[164],"propose":[166],"an":[167],"algorithmic":[168],"framework":[169],"called":[170],"JQODI":[171,209,221],"combining":[172],"time-energy":[174],"tree":[175],"diagram":[176],"represent":[178],"learning":[180],"dynamic":[183],"programming":[184],"solution":[185,213],"data-driven":[189],"theoretical":[190],"approach":[191],"predict":[193],"expected":[195],"total":[196],"number":[197],"training":[199],"epochs":[200],"that":[201,208,220],"meet":[202],"requirements.":[205],"prove":[207],"approximates":[210],"optimal":[212],"polynomial":[215],"complexity.":[216],"Numerical":[217],"results":[218],"demonstrate":[219],"surpasses":[222],"state-of-the-art":[223],"methods":[224],"in":[225],"efficiency":[228],"latency.":[230]},"counts_by_year":[],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2026-05-06T00:00:00"}