{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:58:57Z","timestamp":1781294337351,"version":"3.54.1"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Sichuan Provincial Science and Technology Achievement Transformation","award":["2024ZHCG0009"],"award-info":[{"award-number":["2024ZHCG0009"]}]},{"name":"Sichuan Provincial Science and Technology Achievement Transformation","award":["2026NSFSC1458"],"award-info":[{"award-number":["2026NSFSC1458"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Serv. Comput."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tsc.2026.3681949","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:00:15Z","timestamp":1775592015000},"page":"2303-2316","source":"Crossref","is-referenced-by-count":0,"title":["MccTTA: A Memory-Efficient Collaborative Continual Test-Time Adaptation Framework for Edge Devices"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2467-6480","authenticated-orcid":false,"given":"Haojie","family":"Bai","sequence":"first","affiliation":[{"name":"Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3712-2349","authenticated-orcid":false,"given":"Aiguo","family":"Chen","sequence":"additional","affiliation":[{"name":"Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4119-1575","authenticated-orcid":false,"given":"Yijia","family":"Rong","sequence":"additional","affiliation":[{"name":"Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1074-1952","authenticated-orcid":false,"given":"Jiaxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3511-2582","authenticated-orcid":false,"given":"Kexin","family":"Li","sequence":"additional","affiliation":[{"name":"Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6872-8821","authenticated-orcid":false,"given":"Schahram","family":"Dustdar","sequence":"additional","affiliation":[{"name":"Distributed Systems Group, TU Wien, Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586176"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3308370"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3536311"},{"key":"ref4","first-page":"11285","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Cai","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01196"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01147"},{"key":"ref7","first-page":"15920","article-title":"Dark experience for general continual learning: A strong, simple baseline","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Buzzega","year":"2020"},{"key":"ref8","first-page":"28530","article-title":"Retrospective adversarial replay for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kumari","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111139"},{"key":"ref10","first-page":"2346","article-title":"Memory-efficient patch-based inference for tiny deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lin","year":"2021"},{"key":"ref11","first-page":"29248","article-title":"Back razor: Memory-efficient transfer learning by self-sparsified backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Jiang","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25874"},{"key":"ref13","first-page":"22941","article-title":"On-device training under 256 kb memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lin","year":"2022"},{"key":"ref14","first-page":"6028","article-title":"Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang","year":"2020"},{"key":"ref15","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00706"},{"key":"ref17","article-title":"Test-time adaptation for combating missing modalities in egocentric videos","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Ramazanova","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00852"},{"issue":"PMLR","key":"ref19","first-page":"12878","article-title":"Data-free knowledge distillation for heterogeneous federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02253"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00924"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_25"},{"key":"ref24","first-page":"63268","article-title":"Task-recency bias strikes back: Adapting covariances in exemplar-free class incremental learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Rype\u015b\u0107","year":"2024"},{"key":"ref25","first-page":"2226","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans","year":"2016"},{"key":"ref26","article-title":"Evaluating prediction-time batch normalization for robustness under covariate shift","author":"Nado","year":"2020"},{"key":"ref27","first-page":"21808","article-title":"TTT: When does self-supervised test-time training fail or thrive?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_26"},{"key":"ref29","article-title":"Robust continual test-time adaptation: Instance-aware BN and prediction-balanced memory","author":"Gong","year":"2022"},{"issue":"PMLR","key":"ref30","first-page":"16888","article-title":"Efficient test-time model adaptation without forgetting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Niu","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34133"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02841"},{"key":"ref33","article-title":"RobustBench: A standardized adversarial robustness benchmark","volume-title":"Proc. Neural Inform. Process. Syst. Track Datasets Benchmarks","volume":"1","author":"Croce","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"}],"container-title":["IEEE Transactions on Services Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4629386\/11559165\/11476885.pdf?arnumber=11476885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:42:59Z","timestamp":1781293379000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11476885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":34,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tsc.2026.3681949","relation":{},"ISSN":["1939-1374","2372-0204"],"issn-type":[{"value":"1939-1374","type":"electronic"},{"value":"2372-0204","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}