{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:21:18Z","timestamp":1740169278151,"version":"3.37.3"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100007465","name":"Centre for Integrated Remote Sensing and Forecasting for Arctic Operations (CIRFA) and the Research Council of Norway","doi-asserted-by":"publisher","award":["237906"],"award-info":[{"award-number":["237906"]}],"id":[{"id":"10.13039\/100007465","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union\u2019s Horizon 2020 Research and Innovation Programme Extreme Earth Project","award":["825258"],"award-info":[{"award-number":["825258"]}]},{"name":"Fram Center under the Automised Large-Scale Sea Ice Mapping (ALSIM) through the \u201cPolhavet\u201d Flagship Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3197646","type":"journal-article","created":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T19:50:29Z","timestamp":1659988229000},"page":"84569-84578","source":"Crossref","is-referenced-by-count":1,"title":["AFSD: Adaptive Feature Space Distillation for Distributed Deep Learning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2267-8018","authenticated-orcid":false,"given":"Salman","family":"Khaleghian","sequence":"first","affiliation":[{"name":"Faculty of Science and Technology, UiT The Arctic University of Norway, Tromsø, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2434-0849","authenticated-orcid":false,"given":"Habib","family":"Ullah","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, Norwegian University of Life Sciences (NMBU), Ås, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Einar Broch","family":"Johnsen","sequence":"additional","affiliation":[{"name":"Department of Informatics, University of Oslo, Oslo, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3014-8025","authenticated-orcid":false,"given":"Anders","family":"Andersen","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, UiT The Arctic University of Norway, Tromsø, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6789-0915","authenticated-orcid":false,"given":"Andrea","family":"Marinoni","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, UiT The Arctic University of Norway, Tromsø, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2955494"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3363554"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06156-1_4"},{"key":"ref5","article-title":"Revisiting distributed synchronous SGD","author":"Chen","year":"2016","journal-title":"arXiv:1604.00981"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3059108"},{"key":"ref7","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Alistarh","year":"2017"},{"key":"ref8","first-page":"1","article-title":"Local SGD converges fast and communicates little","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Stich"},{"key":"ref9","first-page":"344","article-title":"Stochastic gradient push for distributed deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Assran"},{"key":"ref10","article-title":"Large scale distributed neural network training through online distillation","author":"Anil","year":"2018","journal-title":"arXiv:1804.03235"},{"key":"ref11","article-title":"Towards understanding ensemble, knowledge distillation and self-distillation in deep learning","author":"Allen-Zhu","year":"2020","journal-title":"arXiv:2012.09816"},{"article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS), Deep Learn. Workshop","author":"Hinton","key":"ref12"},{"key":"ref13","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Huang"},{"key":"ref14","first-page":"1","article-title":"Communication efficient distributed machine learning with the parameter server","volume-title":"Proc. NIPS","volume":"2","author":"Li"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref16","first-page":"1","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","volume":"abs\/1706.02677","author":"Goyal","year":"2017","journal-title":"CoRR"},{"key":"ref17","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","author":"Lian","year":"2017","journal-title":"arXiv:1705.09056"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018769"},{"key":"ref19","article-title":"HOGWILD!: A lock-free approach to parallelizing stochastic gradient descent","author":"Niu","year":"2011","journal-title":"arXiv:1106.5730"},{"key":"ref20","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta"},{"key":"ref21","first-page":"1","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and Huffman coding","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Han"},{"issue":"1","key":"ref22","first-page":"6869","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"Hubara","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1045"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11728"},{"key":"ref25","first-page":"1","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Lin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356222"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2015.04.035"},{"key":"ref28","article-title":"Why m heads are better than one: Training a diverse ensemble of deep networks","author":"Lee","year":"2015","journal-title":"arXiv:1511.06314"},{"key":"ref29","first-page":"1","article-title":"Augmix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Hendrycks"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-614"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412615"},{"key":"ref33","first-page":"1411","article-title":"Feature-level ensemble knowledge distillation for aggregating knowledge from multiple networks","volume-title":"Proc. ECAI","author":"Park"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref34"},{"key":"ref35","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref37"},{"key":"ref38","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Simonyan"},{"key":"ref39","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00521"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3119485"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09852441.pdf?arnumber=9852441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T02:02:45Z","timestamp":1710381765000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9852441\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3197646","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2022]]}}}