{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T05:33:20Z","timestamp":1763444000294,"version":"3.37.3"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grants Council","award":["AoE\/E-601\/22-R"],"award-info":[{"award-number":["AoE\/E-601\/22-R"]}]},{"DOI":"10.13039\/501100010256","name":"Guangzhou Municipal Science and Technology Project","doi-asserted-by":"publisher","award":["2023A03J0011"],"award-info":[{"award-number":["2023A03J0011"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tsp.2023.3252165","type":"journal-article","created":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T18:35:36Z","timestamp":1678300536000},"page":"670-685","source":"Crossref","is-referenced-by-count":7,"title":["Structured Bayesian Compression for Deep Neural Networks Based on the Turbo-VBI Approach"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9774-465X","authenticated-orcid":false,"given":"Chengyu","family":"Xia","sequence":"first","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0135-7098","authenticated-orcid":false,"given":"Danny H. K.","family":"Tsang","sequence":"additional","affiliation":[{"name":"Internet of Things Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7769-6008","authenticated-orcid":false,"given":"Vincent K. N.","family":"Lau","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2019"},{"key":"ref2","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"LeCun","year":"1990"},{"volume-title":"Second Order Derivatives for Network Pruning: Optimal Brain Surgeon","year":"1993","author":"Hassibi","key":"ref3"},{"key":"ref4","article-title":"Learning sparse neural networks through $L\\_{0}$ regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Louizos","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157329"},{"article-title":"An overview of neural network compression","year":"2020","author":"Neill","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.02.029"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref9","first-page":"9865","article-title":"Neuron-level structured pruning using polarization regularizer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhuang","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6138"},{"key":"ref11","first-page":"875","article-title":"Generalization by weight-elimination with application to forecasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Weigend","year":"1991"},{"key":"ref12","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Frankle","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01197"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107988"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICACI55529.2022.9837622"},{"key":"ref16","first-page":"25656","article-title":"Topology-aware network pruning using multi-stage graph embedding and reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2022"},{"key":"ref17","first-page":"20863","article-title":"Red: Looking for redundancies for data-freestructured compression of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yvinec","year":"2021"},{"key":"ref18","first-page":"3259","article-title":"Linear mode connectivity and the lottery ticket hypothesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Frankle","year":"2020"},{"key":"ref19","first-page":"5741","article-title":"Bayesian bits: Unifying quantization and pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baalen","year":"2020"},{"key":"ref20","first-page":"2498","article-title":"Variational dropout sparsifies deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Molchanov","year":"2017"},{"key":"ref21","first-page":"3290","article-title":"Bayesian compression for deep learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Louizos","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2971193"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2010.5464920"},{"key":"ref24","article-title":"Deterministic variational inference for robust Bayesian neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2018"},{"key":"ref25","first-page":"292","article-title":"Eager pruning: Algorithm and architecture support for fast training of deep neural networks","volume-title":"Proc. IEEE\/ACM 46th Annu. Int. Symp. Comput. Architecture","author":"Zhang","year":"2019"},{"article-title":"A note on the group lasso and a sparse group lasso","year":"2010","author":"Friedman","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.643"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00198"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080215"},{"key":"ref30","first-page":"129","article-title":"What is the state of neural network pruning?","volume-title":"Proc. Mach. Learn. Syst.","author":"Blalock","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2022.3155327"},{"key":"ref32","first-page":"467","article-title":"Loopy belief propagation for approximate inference: An empirical study","volume-title":"Proc. 15th Conf. Uncertainty Artif. Intell.","author":"Murphy","year":"2013"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.929620"},{"key":"ref34","first-page":"2575","article-title":"Variational dropout and the local reparameterization trick","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017501703105"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00711"},{"article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","year":"2017","author":"Xiao","key":"ref37"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref38"},{"key":"ref39","first-page":"19655","article-title":"HYDRA: Pruning adversarially robust neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sehwag","year":"2020"},{"key":"ref40","first-page":"361","article-title":"Robust error bounds for quantised and pruned neural networks","volume-title":"Proc. Conf. Learn. Dyn. Control","author":"Li","year":"2021"},{"article-title":"Adversarial robustness of pruned neural networks","year":"2018","author":"Wang","key":"ref41"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/10040758\/10064105.pdf?arnumber=10064105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T10:58:31Z","timestamp":1707821911000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10064105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/tsp.2023.3252165","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2023]]}}}