{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T10:36:45Z","timestamp":1778495805980,"version":"3.51.4"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T00:00:00Z","timestamp":1616630400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T00:00:00Z","timestamp":1616630400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Comput Sci"],"DOI":"10.1038\/s43588-021-00039-6","type":"journal-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T18:40:05Z","timestamp":1616697605000},"page":"221-228","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Random sketch learning for deep neural networks in edge computing"],"prefix":"10.1038","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1998-819X","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"first","affiliation":[]},{"given":"Peijun","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3543-9916","authenticated-orcid":false,"given":"Hongfu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Weisi","family":"Guo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5042-7884","authenticated-orcid":false,"given":"Xianbin","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Junzhao","family":"Du","sequence":"additional","affiliation":[]},{"given":"Chenglin","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,3,25]]},"reference":[{"key":"39_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun, Y., Bengio, Y. & Hinton, G. E. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"39_CR2","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D. et al. Mastering the game of Go with deep neural networks and tree search. Nature 529, 484\u2013489 (2016).","journal-title":"Nature"},{"key":"39_CR3","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41586-019-0912-1","volume":"566","author":"M Reichstein","year":"2019","unstructured":"Reichstein, M. et al. Deep learning and process understanding for data-driven Earth system science. Nature 566, 195\u2013204 (2019).","journal-title":"Nature"},{"key":"39_CR4","doi-asserted-by":"publisher","first-page":"2204","DOI":"10.1109\/JPROC.2019.2941458","volume":"107","author":"P Jihong","year":"2019","unstructured":"Jihong, P., Samarakoon, S., Mehdi, B. & Debba, M. Wireless network intelligence at the edge. Proc. IEEE 107, 2204\u20132239 (2019).","journal-title":"Proc. IEEE"},{"key":"39_CR5","unstructured":"Hiroshi, D. & Roberto, M. TinyML as-a-Service: What is it and what does it mean for the IoT Edge? Ericsson https:\/\/www.ericsson.com\/en\/blog\/2019\/12\/tinyml-as-a-service-iot-edge (2019)."},{"key":"39_CR6","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1038\/s41928-018-0198-6","volume":"2","author":"O Vaughan","year":"2019","unstructured":"Vaughan, O. Working on the edge. Nat. Electron. 2, 2\u20133 (2019).","journal-title":"Nat. Electron."},{"key":"39_CR7","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1038\/s41586-020-2442-2","volume":"583","author":"B Burger","year":"2020","unstructured":"Burger, B. et al. A mobile robotic chemist. Nature 583, 237\u2013241 (2020).","journal-title":"Nature"},{"key":"39_CR8","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.jmsy.2018.01.003","volume":"48","author":"J Wang","year":"2018","unstructured":"Wang, J., Ma, Y., Zhang, L., Gao, R. X. & Wu, D. Deep learning for smart manufacturing: methods and applications. J. Manuf. Syst. 48, 144\u2013156 (2018).","journal-title":"J. Manuf. Syst."},{"key":"39_CR9","doi-asserted-by":"publisher","first-page":"B05307","DOI":"10.1029\/2008JB006088","volume":"114","author":"FJ Simons","year":"2009","unstructured":"Simons, F. J. et al. On the potential of recording earthquakes for global seismic tomography by low-cost autonomous instruments in the oceans. J. Geophys. Res. Solid Earth 114, B05307 (2009).","journal-title":"J. Geophys. Res. Solid Earth"},{"key":"39_CR10","doi-asserted-by":"publisher","unstructured":"Kiran, B. R. et al. Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transport. Syst. https:\/\/doi.org\/10.1109\/TITS.2021.3054625 (2021).","DOI":"10.1109\/TITS.2021.3054625"},{"key":"39_CR11","doi-asserted-by":"publisher","unstructured":"Weiss, B. A., Pellegrino, J., Justiniano, M. & Raghunatha, A. Measurement Science Roadmap for Prognostics and Health Management for Smart Manufacturing Systems (National Institute of Standards and Technology, 2016); https:\/\/doi.org\/10.6028\/NIST.AMS.100-2","DOI":"10.6028\/NIST.AMS.100-2"},{"key":"39_CR12","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.ymssp.2015.04.021","volume":"64","author":"WA Smith","year":"2015","unstructured":"Smith, W. A. & Randall, R. B. Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study. Mech. Syst. Signal Process. 64, 100\u2013131 (2015).","journal-title":"Mech. Syst. Signal Process."},{"key":"39_CR13","unstructured":"Hiroshi, D., Roberto, M. & H\u00f6ller, J. Bringing machine learning to the deepest IoT edge with TinyML as-a-service. IEEE IoT Newsletter\u2014March 2020 (2020)."},{"key":"39_CR14","unstructured":"Hiroshi, D. & Roberto, M. TinyML as a service and the challenges of machine learning at the edge. Ericsson https:\/\/www.ericsson.com\/en\/blog\/2019\/12\/tinyml-as-a-service (2019)."},{"key":"39_CR15","unstructured":"Ward-Foxton, S. Adapting the microcontroller for AI in the endpoint. EE Times https:\/\/www.eetimes.com\/adapting-the-microcontroller-for-ai-in-the-endpoint\/ (2020)."},{"key":"39_CR16","unstructured":"Loukides, M. TinyML: the challenges and opportunities of low-power ML applications. O\u2019Reilly https:\/\/www.oreilly.com\/radar\/tinyml-the-challenges-and-opportunities-of-low-power-ml-applications\/ (2019)."},{"key":"39_CR17","unstructured":"Reddi, V. J. Enabling ultra-low power machine learning at the edge. In TinyML Summit 2020 (TinyML, 2020); https:\/\/cms.tinyml.org\/wp-content\/uploads\/summit2020\/tinyMLSummit2020-4-4-JanapaReddi.pdf"},{"key":"39_CR18","unstructured":"Koehler, G. MNIST handwritten digit recognition in Keras. Nextjournal https:\/\/nextjournal.com\/gkoehler\/digit-recognition-with-keras (2020)."},{"key":"39_CR19","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1038\/s41928-018-0059-3","volume":"1","author":"X Xu","year":"2018","unstructured":"Xu, X. et al. Scaling for edge inference of deep neural networks. Nat. Electron. 1, 216\u2013222 (2018).","journal-title":"Nat. Electron."},{"key":"39_CR20","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","volume":"105","author":"V Sze","year":"2017","unstructured":"Sze, V., Chen, Y. H., Yang, T. J. & Emer, J. S. Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105, 2295\u20132329 (2017).","journal-title":"Proc. IEEE"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Gao, M., Pu, J., Yang, X., Horowitz, M. & Kozyrakis, C. Tetris: scalable and efficient neural network acceleration with 3D memory. In Proc. 22nd International Conference on Architectural Support for Programming Languages and Operating Systems Vol. 45, 751\u2013764 (ACM, 2017).","DOI":"10.1145\/3093337.3037702"},{"key":"39_CR22","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1038\/s41928-017-0002-z","volume":"1","author":"C Li","year":"2018","unstructured":"Li, C., Miao, H., Li, Y., Hao, J. & Xia, Q. Analogue signal and image processing with large memristor crossbars. Nat. Electron. 1, 52\u201359 (2018).","journal-title":"Nat. Electron."},{"key":"39_CR23","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1038\/nature14441","volume":"521","author":"M Prezioso","year":"2015","unstructured":"Prezioso, M. et al. Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature 521, 61\u201364 (2015).","journal-title":"Nature"},{"key":"39_CR24","unstructured":"NVIDIA Tesla P100. NVIDIA www.nvidia.com\/object\/tesla-p100.html (2017)."},{"key":"39_CR25","unstructured":"Han, S., Pool, J., Tran, J. & Dally, W. J. Learning both weights and connections for efficient neural networks. In Proc. Neural Information Processing Systems 1135\u20131143 (NIPS, 2015)."},{"key":"39_CR26","unstructured":"Wen, W., Wu, C., Wang, Y., Chen, Y. & Li, H. Learning structured sparsity in deep neural networks. In Proc. Neural Information Processing Systems 2074\u20132082 (NIPS, 2016)."},{"key":"39_CR27","unstructured":"Han, S., Mao, H. & Dally, W. J. Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. In Proc. International Conference on Learning Representations 1\u201314 (ICLR, 2015)."},{"key":"39_CR28","unstructured":"Frankle, J. & Carbin, M. The lottery ticket hypothesis: finding sparse, trainable neural networks. In Proc. International Conference on Learning Representations 1\u201342 (ICLR, 2018)."},{"key":"39_CR29","unstructured":"Lee, N., Thalaiyasingam, A. & Torr, P. H. SNIP: single-shot network pruning based on connection sensitivity. In Proc. International Conference on Learning Representations 1\u201315 (ICLR, 2019)."},{"key":"39_CR30","unstructured":"Denil, M., Shakibi, B., Dinh, L., Ranzato, M. & De Freitas, N. Predicting parameters in deep learning. In Proc. Neural Information Processing Systems 2148\u20132156 (NIPS, 2013)."},{"key":"39_CR31","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A. & Zisserman, A. Speeding up convolutional neural networks with low rank expansions. In Proc. British Machine Vision Conference 1\u201313 (BMVC, 2014).","DOI":"10.5244\/C.28.88"},{"key":"39_CR32","unstructured":"Zhou, T. & Tao, D. GoDec: randomized low-rank & sparse matrix decomposition in noisy case. In Proc. International Conference on Machine Learning 33\u201340 (ICML, 2011)."},{"key":"39_CR33","doi-asserted-by":"crossref","unstructured":"Yu, X., Liu, T., Wang, X. & Tao, D. On compressing deep models by low rank and sparse decomposition. In Proc. International Conference on Computer Vision and Pattern Recognition 67\u201376 (CVPR, 2017).","DOI":"10.1109\/CVPR.2017.15"},{"key":"39_CR34","doi-asserted-by":"crossref","unstructured":"Lee, E. H., Miyashita, D., Chai, E., Murmann, B. & Wong, S. S. LogNet: energy-efficient neural networks using logarithmic computation. In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing 5900\u20135904 (IEEE, 2017).","DOI":"10.1109\/ICASSP.2017.7953288"},{"key":"39_CR35","unstructured":"Dong, X. & Yang, Y. Network pruning via transformable architecture search. In Proc. Neural Information Processing Systems 760\u2013771 (NIPS, 2019)."},{"key":"39_CR36","unstructured":"Guo, Y. et al. NAT: neural architecture transformer for accurate and compact architectures. In Proc. Neural Information Processing Systems 737\u2013748 (NIPS, 2019)."},{"key":"39_CR37","unstructured":"Blalock, D. W., Ortiz, J. J. G., Frankle, J. & Guttag, J. V. What is the state of neural network pruning? in Proceedings of Machine Learning and Systems 2020 (MLSys) 1-18 (2020)."},{"key":"39_CR38","first-page":"1","volume":"10","author":"Q Yang","year":"2019","unstructured":"Yang, Q. et al. Federated machine learning: concept and applications. ACM Trans. Intell. Syst. Technol. 10, 1\u201319 (2019).","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"39_CR39","unstructured":"Bonawitz, K. et al. Practical secure aggregation for federated learning on user-held data. In Proc. Neural Information Processing Systems (NIPS, 2016)."},{"key":"39_CR40","doi-asserted-by":"crossref","unstructured":"Silva, S., Gutman, B. A., Romero, E., Thompson, P. M. & Lorenzi, M. Federated learning in distributed medical databases: meta-analysis of large-scale subcortical brain data. In Proc. IEEE International Symposium on Biomedical Imaging 270\u2013274 (IEEE, 2019).","DOI":"10.1109\/ISBI.2019.8759317"},{"key":"39_CR41","unstructured":"Mcmahan, H. B., Moore, E., Ramage, D., Hampson, S. & Ag\u00fcera y Arcas, B. Communication-efficient learning of deep networks from decentralized data. In Proc. 20th International Conference on Artificial Intelligence and Statistics 1\u201311 (AISTATS, 2017)."},{"key":"39_CR42","unstructured":"Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. In Proc. International Conference on Learning Representations 1\u201314 (ICLR, 2015)."},{"key":"39_CR43","doi-asserted-by":"crossref","unstructured":"Lym, S. et al. PruneTrain: fast neural network training by dynamic sparse model reconfiguration. In Proc. International Conference for High Performance Computing, Networking, Storage and Analysis 1\u201313 (ACM, 2019).","DOI":"10.1145\/3295500.3356156"},{"key":"39_CR44","doi-asserted-by":"publisher","unstructured":"Lu, Y., Huang, X., Zhang, K., Maharjan, S. & Zhang, Y. Low-latency federated learning and blockchain for edge association in digital twin empowered 6G networks. IEEE Trans. Industr. Inform. https:\/\/doi.org\/10.1109\/TII.2020.3017668 (2020).","DOI":"10.1109\/TII.2020.3017668"},{"key":"39_CR45","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.ijmedinf.2018.01.007","volume":"112","author":"TS Brisimi","year":"2018","unstructured":"Brisimi, T. S. et al. Federated learning of predictive models from federated electronic health records. Int. J. Med. Inform. 112, 59\u201367 (2018).","journal-title":"Int. J. Med. Inform."},{"key":"39_CR46","unstructured":"Glorot, X. & Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. In Proc. Thirteenth International Conference on Artificial Intelligence and Statistics 249\u2013256 (JMLR, 2010)."},{"key":"39_CR47","first-page":"2729","volume":"14","author":"S Wang","year":"2013","unstructured":"Wang, S. & Zhang, Z. Improving CUR matrix decomposition and the nystr\u00f6m approximation via adaptive sampling. J. Mach. Learn. Res. 14, 2729\u20132769 (2013).","journal-title":"J. Mach. Learn. Res."},{"key":"39_CR48","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1137\/07070471X","volume":"30","author":"P Drineas","year":"2008","unstructured":"Drineas, P., Mahoney, M. W. & Muthukrishnan, S. Relative-error CUR matrix decompositions. SIAM J. Matrix Anal. Appl. 30, 844\u2013881 (2008).","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"39_CR49","doi-asserted-by":"publisher","first-page":"2314","DOI":"10.1109\/LCOMM.2020.3001931","volume":"24","author":"B Li","year":"2020","unstructured":"Li, B. et al. Randomized approximate channel estimator in massive-MIMO communication. IEEE Commun. Lett. 24, 2314\u20132318 (2020).","journal-title":"IEEE Commun. Lett."},{"key":"39_CR50","unstructured":"Li, B. et al. Fast-MUSIC for automotive massive-MIMO radar. Preprint at https:\/\/arxiv.org\/abs\/1911.07434 (2019)."},{"key":"39_CR51","unstructured":"Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. In Proc. International Conference on Learning Representations 1\u201315 (ICLR, 2015)."},{"key":"39_CR52","doi-asserted-by":"publisher","unstructured":"Li, B., Liu, H. & Chen, P. Random sketch learning for tiny AI. Code Ocean https:\/\/doi.org\/10.24433\/CO.5227764.v1 (2021).","DOI":"10.24433\/CO.5227764.v1"}],"container-title":["Nature Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43588-021-00039-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-021-00039-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43588-021-00039-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T21:22:55Z","timestamp":1670102575000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43588-021-00039-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,25]]},"references-count":52,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,3]]}},"alternative-id":["39"],"URL":"https:\/\/doi.org\/10.1038\/s43588-021-00039-6","relation":{},"ISSN":["2662-8457"],"issn-type":[{"value":"2662-8457","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,25]]},"assertion":[{"value":"7 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}