{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:13:27Z","timestamp":1781482407562,"version":"3.54.1"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Research Grants Council of the Hong Kong Special Administrative Region, China","doi-asserted-by":"publisher","award":["CityU 11214020"],"award-info":[{"award-number":["CityU 11214020"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council of the Hong Kong Special Administrative Region, China","doi-asserted-by":"publisher","award":["C1020-19E"],"award-info":[{"award-number":["C1020-19E"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council of the Hong Kong Special Administrative Region, China","doi-asserted-by":"publisher","award":["CityU 11215618"],"award-info":[{"award-number":["CityU 11215618"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council of the Hong Kong Special Administrative Region, China","doi-asserted-by":"publisher","award":["UST 16200021"],"award-info":[{"award-number":["UST 16200021"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tnnls.2022.3217403","type":"journal-article","created":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T22:34:07Z","timestamp":1667860447000},"page":"8999-9013","source":"Crossref","is-referenced-by-count":7,"title":["Power Law in Deep Neural Networks: Sparse Network Generation and Continual Learning With Preferential Attachment"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3043-2360","authenticated-orcid":false,"given":"Fan","family":"Feng","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and the State Key Laboratory of Terahertz and Millimeter Waves, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4694-1821","authenticated-orcid":false,"given":"Lu","family":"Hou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4490-2941","authenticated-orcid":false,"given":"Qi","family":"She","sequence":"additional","affiliation":[{"name":"Bytedance AI Lab, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4808-2490","authenticated-orcid":false,"given":"Rosa H. M.","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and the State Key Laboratory of Terahertz and Millimeter Waves, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4828-8248","authenticated-orcid":false,"given":"James T.","family":"Kwok","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","first-page":"598","article-title":"Optimal brain damage","volume-title":"Advances in Neural Information Processing Systems","author":"LeCun","year":"1990"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.l803.03635"},{"key":"ref4","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"4th Int. Conf. Learn. Representations (ICLR)","author":"Han"},{"key":"ref5","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Advances in Neural Information Processing Systems","author":"Han"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2906563"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3084206"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-4371(02)00736-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/science.286.5439.509"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.94.018102"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1086\/503294"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0503-60"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref16","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Tan"},{"key":"ref17","first-page":"10881","article-title":"Graph structure of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"You"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00137"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_2"},{"key":"ref20","first-page":"1","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","first-page":"1379","article-title":"Dynamic network surgery for efficient DNNs","volume-title":"Advances in Neural Information Processing Systems","author":"Guo"},{"key":"ref22","first-page":"2498","article-title":"Variational dropout sparsifies deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Molchanov"},{"key":"ref23","first-page":"211","article-title":"Sparse Bayesian learning and the relevance vector machine","volume":"1","author":"Tipping","year":"2001","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","first-page":"2","article-title":"Stochastic backpropagation and variational inference in deep latent Gaussian models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"2","author":"Rezende"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.06.025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.09.061"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3049056"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281839"},{"key":"ref29","first-page":"1","article-title":"Pruning filters for efficient ConvNets","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref31","first-page":"1","article-title":"Pruning convolutional neural networks for resource efficient inference","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Molchanov"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107899"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01604"},{"key":"ref34","first-page":"1","article-title":"Playing the lottery with rewards and multiple languages: Lottery tickets in RL and NLP","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yu"},{"key":"ref35","first-page":"15834","article-title":"The lottery ticket hypothesis for pre-trained bert networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Chen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/int.22827"},{"key":"ref37","first-page":"12356","article-title":"Can subnetwork structure be the key to out-of-distribution generalization?","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhang"},{"key":"ref38","first-page":"6682","article-title":"Proving the lottery ticket hypothesis: Pruning is all you need","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Malach"},{"key":"ref39","first-page":"1","article-title":"Network pruning that matters: A case study on retraining variants","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Le"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2342533"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196887"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2011.2177670"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2900956"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3151511"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.021"},{"key":"ref48","article-title":"Don\u2019t forget, there is more than forgetting: New metrics for continual learning","author":"D\u00edaz-Rodr\u00edguez","year":"2018","journal-title":"arXiv:1810.13166"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3007548"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3042500"},{"key":"ref54","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zenke"},{"key":"ref55","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arxiv:1606.04671"},{"key":"ref56","first-page":"1","article-title":"Lifelong learning with dynamically expandable networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yoon"},{"key":"ref57","article-title":"PathNet: Evolution channels gradient descent in super neural networks","author":"Fernando","year":"2017","journal-title":"arxiv:1701.08734"},{"key":"ref58","first-page":"1","article-title":"Experience replay for continual learning","volume":"32","author":"Rolnick","year":"2019","journal-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072041"},{"key":"ref61","first-page":"1","article-title":"Efficient lifelong learning with a-GEM","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chaudhry"},{"key":"ref62","first-page":"1","article-title":"Continual learning with deep generative replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"30","author":"Shin"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3111019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3010581"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927369"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3057453"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1137\/070710111"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.96.018702"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1080\/00107510500052444"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1038\/srep01783"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2010.04.020"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2202-12-S1-O4"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000748"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-08746-5"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/PL00001202"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.200327197"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2007.10.060"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1126\/science.281.5384.1840"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s00024-013-0644-3"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0170920"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/62.1.5"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970586"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.2307\/2283970"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1969.10500983"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1140\/epjb\/e2004-00316-5"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.2478\/s11600-013-0154-9"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref89","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Simonyan"},{"key":"ref90","first-page":"1059","article-title":"High-performance large-scale image recognition without normalization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Brock"},{"key":"ref91","first-page":"4284","article-title":"Traditional and heavy tailed self regularization in neural network models","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Martin"},{"key":"ref92","article-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","author":"Goodfellow","year":"2013","journal-title":"arXiv:1312.6211"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"ref94","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref96","first-page":"1","article-title":"Pruning convolutional neural networks for resource efficient transfer learning","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Molchanov"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref98","first-page":"1","article-title":"Growing efficient deep networks by structured continuous sparsification","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yuan"},{"key":"ref99","first-page":"1","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals"},{"key":"ref100","article-title":"On tiny episodic memories in continual learning","author":"Chaudhry","year":"2019","journal-title":"arXiv:1902.10486"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10589508\/09941061.pdf?arnumber=9941061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T05:01:45Z","timestamp":1720587705000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9941061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":100,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3217403","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}