{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:06:51Z","timestamp":1780949211697,"version":"3.54.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grants Council of Hong Kong","award":["27213824"],"award-info":[{"award-number":["27213824"]}]},{"name":"Research Grants Council of Hong Kong","award":["CRS HKU702\/24"],"award-info":[{"award-number":["CRS HKU702\/24"]}]},{"name":"Research Grants Council of the Hong Kong Special Administrative Region, China","award":["HKU RFS2122-7S04"],"award-info":[{"award-number":["HKU RFS2122-7S04"]}]},{"name":"NSFC\/RGC CRS","award":["CRS_HKU702\/24"],"award-info":[{"award-number":["CRS_HKU702\/24"]}]},{"name":"Areas of Excellence Scheme","award":["AoE\/E-601\/22-R"],"award-info":[{"award-number":["AoE\/E-601\/22-R"]}]},{"name":"Collaborative Research Fund","award":["C1009-22G"],"award-info":[{"award-number":["C1009-22G"]}]},{"name":"Collaborative Research Fund","award":["17212423"],"award-info":[{"award-number":["17212423"]}]},{"name":"Collaborative Research Fund","award":["17304925"],"award-info":[{"award-number":["17304925"]}]},{"name":"Croucher Senior Fellowship and Shenzhen-Hong Kong-Macau Technology Research Programme","award":["SGDX20230821091559018"],"award-info":[{"award-number":["SGDX20230821091559018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tmc.2026.3664415","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T20:52:02Z","timestamp":1771015922000},"page":"10924-10938","source":"Crossref","is-referenced-by-count":1,"title":["SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6332-6222","authenticated-orcid":false,"given":"Qian","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4295-940X","authenticated-orcid":false,"given":"Xianhao","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8773-4629","authenticated-orcid":false,"given":"Kaibin","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Introducing ChatGPT"},{"key":"ref2","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3564163"},{"key":"ref4","first-page":"582","article-title":"Semantic sleuth: Identifying ponzi contracts via large language models","volume-title":"Proc. IEEE\/ACM Int. Conf. Autom. Softw. Eng.","author":"Wu","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TON.2025.3526148"},{"key":"ref6","article-title":"On-device language models: A comprehensive review","author":"Xu","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2026.3680521"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3527641"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2400764"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3719664"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2026.3680521"},{"key":"ref12","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref13","article-title":"Mixtral of experts","author":"Jiang","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3554028"},{"issue":"120","key":"ref15","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS60910.2024.00013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3493800"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.014.2300400"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2023.3269769"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2026.3654458"},{"key":"ref21","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"35","author":"Lu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3365465"},{"issue":"16","key":"ref23","doi-asserted-by":"crossref","first-page":"26580","DOI":"10.1109\/JIOT.2024.3355139","volume":"11","author":"Zhu","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2023.3305195"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2281606"},{"key":"ref26","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shazeer","year":"2017"},{"key":"ref27","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lepikhin","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.696"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676741"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3546466"},{"key":"ref31","article-title":"ExpertFlow: Optimized expert activation and token allocation for efficient mixture-of-experts inference","author":"He","year":"2024"},{"key":"ref32","article-title":"Read-ME: Refactorizing LLMs as router-decoupled mixture of experts with system co-design","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Cai","year":"2024"},{"key":"ref33","article-title":"Optimal expert selection for distributed mixture-of-experts at the wireless edge","author":"Qin","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3253255"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3233532"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3387548"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3104015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3307769"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ton.2026.3688811"},{"key":"ref40","first-page":"204","article-title":"Parameters vs FLOPs: Scaling laws for optimal sparsity for mixture-of-experts language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abnar","year":"2025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3239189"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00086"},{"key":"ref43","first-page":"17555","article-title":"Hash layers for large sparse models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Roller"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.890"},{"key":"ref45","first-page":"98:1","article-title":"Simple deterministic approximation for submodular multiple knapsack problem","volume-title":"Proc. Annu. Eur. Symp. Algorithms","volume":"274","author":"Sun","year":"2023"},{"key":"ref46","first-page":"19:1","article-title":"Capacitated dynamic programming: Faster knapsack and graph algorithms","volume-title":"Proc. Int. Colloq. Automata Lang. Program.","volume":"132,","author":"Axiotis","year":"2019"},{"key":"ref47","first-page":"304","article-title":"Greed is still good: Maximizing monotone submodular supermodular (BP) functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bai","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-021-01123-x"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3024629"},{"key":"ref50","article-title":"FDD base station (BS) classification","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2869562"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11552380\/11395617.pdf?arnumber=11395617","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:32Z","timestamp":1780948472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11395617\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":52,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2026.3664415","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}