{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:07:11Z","timestamp":1761894431700,"version":"build-2065373602"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"European Chips Joint Undertaking through Framework Partnership","award":["02.045081801 (RIGOLETTO)"],"award-info":[{"award-number":["02.045081801 (RIGOLETTO)"]}]},{"name":"German Federal Ministry of Research, Technology and Space","award":["16MEE0549 (RIGOLETTO)"],"award-info":[{"award-number":["16MEE0549 (RIGOLETTO)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. VLSI Syst."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tvlsi.2025.3611822","type":"journal-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T17:39:55Z","timestamp":1758908395000},"page":"2975-2983","source":"Crossref","is-referenced-by-count":0,"title":["General Compilation and Mixed-Precision Partitioning: A Combined Approach for Adaptive On-Device Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8730-2460","authenticated-orcid":false,"given":"Iuliia","family":"Topko","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1700-5778","authenticated-orcid":false,"given":"Fabian","family":"Kre\u00df","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tanja","family":"Harbaum","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5082-5487","authenticated-orcid":false,"given":"J\u00fcrgen","family":"Becker","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Privacy-preserving machine learning: Methods, challenges and directions","author":"Xu","year":"2021","journal-title":"arXiv:2108.04417"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3696003"},{"key":"ref6","article-title":"On-device machine learning: An algorithms and learning theory perspective","author":"Dhar","year":"2019","journal-title":"arXiv:1911.00623"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/NorCAS64408.2024.10752456"},{"key":"ref8","article-title":"How transferable are features in deep neural networks?","author":"Yosinski","year":"2014","journal-title":"arXiv:1411.1792"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25874"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csi.2024.103906"},{"key":"ref11","article-title":"On-device training empowered transfer learning for human activity recognition","author":"Kang","year":"2024","journal-title":"arXiv:2407.03644"},{"key":"ref12","first-page":"11285","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Cai"},{"key":"ref13","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Xiao"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2021.3114881"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3058217"},{"volume-title":"Tensorflow Lite Inference","year":"2024","key":"ref16"},{"volume-title":"On-Device Training With Tensorflow Lite","year":"2024","key":"ref17"},{"volume-title":"Tensorflow Lite for Microcontrollers","year":"2024","key":"ref18"},{"volume-title":"Ai Speech Recognition With Tensorflow Lite for Microcontrollers and Sparkfun Edge","year":"2024","key":"ref19"},{"key":"ref20","first-page":"1","article-title":"MiniLearn: On-device learning for low-power IoT devices","volume-title":"Proc. Int. Conf. Embedded Wireless Syst. Netw.","author":"Profentzas"},{"key":"ref21","first-page":"1","article-title":"TinyOL: TinyML with online-learning on microcontrollers","volume-title":"Proc. Int. Joint Conf. Neural Netw. (IJCNN)","author":"Ren"},{"article-title":"On-device training under 256KB memory","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Lin","key":"ref22"},{"volume-title":"An Overview of TVM and Model Optimization","year":"2023","author":"TVM","key":"ref23"},{"volume-title":"Introduction to Algorithms","year":"2022","author":"Cormen","key":"ref24"},{"volume-title":"Exploring Network Structure, Dynamics, and Function Using Networkx","author":"Hagberg","key":"ref25","doi-asserted-by":"crossref","DOI":"10.25080\/TCWV9851"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3078408"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI61997.2024.00019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177011077"},{"volume-title":"Scipy\u2019s Dual\\_Annealing Function","year":"2025","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"volume-title":"Dogs Vs. Cats","year":"2013","author":"Cukierski","key":"ref31"},{"volume-title":"Flowers Dataset","year":"2024","key":"ref32"},{"volume-title":"Verilator","year":"2024","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref36","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Coates"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1602.07360"}],"container-title":["IEEE Transactions on Very Large Scale Integration (VLSI) Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/92\/11222394\/11180921.pdf?arnumber=11180921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:27:16Z","timestamp":1761888436000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11180921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":38,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tvlsi.2025.3611822","relation":{},"ISSN":["1063-8210","1557-9999"],"issn-type":[{"type":"print","value":"1063-8210"},{"type":"electronic","value":"1557-9999"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}