{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T04:02:38Z","timestamp":1750910558147,"version":"3.41.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,20]]},"DOI":"10.1109\/msn63567.2024.00102","type":"proceedings-article","created":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T17:30:15Z","timestamp":1750786215000},"page":"722-729","source":"Crossref","is-referenced-by-count":0,"title":["DOME: Dynamic Optimization of GPU Memory for Training DNN Models with Limited Resources"],"prefix":"10.1109","author":[{"given":"Zijun","family":"Ma","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,Changsha,China"}]},{"given":"Songlei","family":"Jian","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,Changsha,China"}]},{"given":"Yusong","family":"Tan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,Changsha,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2024.3373763"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.10.025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00241"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00801"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5924"},{"key":"ref8","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"ref9","article-title":"A survey of model compression and acceleration for deep neural networks","author":"Cheng","year":"2017","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref11","article-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"7937","article-title":"Memory-efficient pipeline-parallel dnn training","volume-title":"International Conference on Machine Learning. PMLR","author":"Narayanan","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3442442.3452055"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378530"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3193867"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00066"},{"key":"ref18","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"497","article-title":"Checkmate: Breaking the memory wall with optimal tensor rematerialization","volume-title":"Proceedings of Machine Learning and Systems","volume":"2","author":"Jain","year":"2020"},{"key":"ref20","article-title":"Dynamic tensor rematerialization","volume-title":"International Conference on Learning Representations","author":"Kirisame","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651330"},{"key":"ref23","first-page":"23 844","article-title":"Efficient combination of rematerialization and offloading for training dnns","volume":"34","author":"Beaumont","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3266110"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3180991"},{"key":"ref26","article-title":"Delta: Dynamically optimizing gpu memory beyond tensor recomputation","author":"Tang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178491"},{"key":"ref30","article-title":"Coop: Memory is not a commodity","volume":"36","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640423"},{"key":"ref32","first-page":"551","article-title":"{Zero-offload}: Democratizing {billion-scale} model training","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Ren","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00076"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/954339.954341"}],"event":{"name":"2024 20th International Conference on Mobility, Sensing and Networking (MSN)","start":{"date-parts":[[2024,12,20]]},"location":"Harbin, China","end":{"date-parts":[[2024,12,22]]}},"container-title":["2024 20th International Conference on Mobility, Sensing and Networking (MSN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11036321\/11036274\/11036359.pdf?arnumber=11036359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T05:27:34Z","timestamp":1750829254000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11036359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,20]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/msn63567.2024.00102","relation":{},"subject":[],"published":{"date-parts":[[2024,12,20]]}}}