{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T05:48:45Z","timestamp":1773553725333,"version":"3.50.1"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information & communications Technology Planning & Evaluation"},{"name":"Korea government","award":["No.RS-2022-II220184"],"award-info":[{"award-number":["No.RS-2022-II220184"]}]},{"name":"Development and Study of AI Technologies to Inexpensively Conform to Evolving Policy on Ethics"},{"name":"Institute of Information & Communications Technology Planning & Evaluation"},{"name":"Korea government","award":["RS-2021-II211341"],"award-info":[{"award-number":["RS-2021-II211341"]}]},{"name":"Artificial Intelligence Graduate School Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3623953","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:57:35Z","timestamp":1760983055000},"page":"187373-187382","source":"Crossref","is-referenced-by-count":1,"title":["Sparse MoE Students for Efficient Knowledge Distillation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9527-0774","authenticated-orcid":false,"given":"Jongwon","family":"Ryu","sequence":"first","affiliation":[{"name":"Department of AI, Chung-Ang University, Seoul, Republic of Korea"}]},{"given":"Mingi","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of AI, Chung-Ang University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7871-9627","authenticated-orcid":false,"given":"Junyeong","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of AI, Chung-Ang University, Seoul, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3700439"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"ref7","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Deep Learn. Represent. Learn. Workshop","author":"Hinton"},{"key":"ref8","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. ICLR","author":"Romero"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01465"},{"key":"ref11","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv:1701.06538"},{"key":"ref12","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume-title":"Proc. ICLR","author":"Fedus"},{"key":"ref13","volume-title":"CIFAR-10 and CIFAR-100 Datasets","author":"Krizhevsky","year":"2009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref15","article-title":"Knowledge distillation based on transformed teacher matching","author":"Zheng","year":"2024","journal-title":"arXiv:2402.11148"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00358"},{"key":"ref17","first-page":"10170","article-title":"Revisit the power of vanilla knowledge distillation: From small scale to large scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Hao"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref19","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","volume-title":"Proc. ICLR","author":"Lepikhin"},{"key":"ref20","first-page":"5547","article-title":"GLaM: Efficient scaling of language models with mixture-of-experts","volume-title":"Proc. ICML","author":"Du"},{"key":"ref21","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. NeurIPS","author":"Riquelme"},{"key":"ref22","article-title":"Learning deep mixtures of experts","volume-title":"Proc. ICLR Workshop","author":"Marc\u2019Aurelio Ranzato"},{"key":"ref23","article-title":"ST-MoE: designing stable and transferable sparse expert models","author":"Zoph","year":"2022","journal-title":"arXiv:2202.08906"},{"key":"ref24","article-title":"Routing networks: Adaptive selection of non-linear functions for multi-task learning","volume-title":"Proc. ICLR","author":"Rosenbaum"},{"key":"ref25","first-page":"288","article-title":"Megablocks: Efficient sparse training with mixture-of-experts","volume-title":"Proc. ICML","author":"Gale"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26284-5_24"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3125320"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3554028"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11208632.pdf?arnumber=11208632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:49:58Z","timestamp":1762800598000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208632\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3623953","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}