{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T20:06:03Z","timestamp":1758398763616,"version":"3.40.2"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T00:00:00Z","timestamp":1705968000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T00:00:00Z","timestamp":1705968000000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s11432-022-3807-9","type":"journal-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:02:36Z","timestamp":1706767356000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["SWG: an architecture for sparse weight gradient computation"],"prefix":"10.1007","volume":"67","author":[{"given":"Weiwei","family":"Wu","sequence":"first","affiliation":[]},{"given":"Fengbin","family":"Tu","sequence":"additional","affiliation":[]},{"given":"Xiangyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shaojun","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Shouyi","family":"Yin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,23]]},"reference":[{"key":"3807_CR1","doi-asserted-by":"publisher","first-page":"112102","DOI":"10.1007\/s11432-023-3823-6","volume":"67","author":"Z-H Zhou","year":"2024","unstructured":"Zhou Z-H, Tan Z-H. Learnware: small models do big. Sci China Inf Sci, 2024, 67: 112102","journal-title":"Sci China Inf Sci"},{"key":"3807_CR2","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. Commun ACM, 2017, 60: 84\u201390","journal-title":"Commun ACM"},{"doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015. 1\u20139","key":"3807_CR3","DOI":"10.1109\/CVPR.2015.7298594"},{"doi-asserted-by":"crossref","unstructured":"He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. 770\u2013778","key":"3807_CR4","DOI":"10.1109\/CVPR.2016.90"},{"unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. ArXiv:1409.1556","key":"3807_CR5"},{"doi-asserted-by":"crossref","unstructured":"Venkataramani S, Ranjan A, Banerjee S, et al. SCALEDEEP: a scalable compute architecture for learning and evaluating deep networks. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, 2017. 13\u201326","key":"3807_CR6","DOI":"10.1145\/3079856.3080244"},{"doi-asserted-by":"crossref","unstructured":"Chen Y J, Luo T, Liu S L, et al. DaDianNao: a machine-learning supercomputer. In: Proceedings of the 47th Annual IEEE\/ACM International Symposium on Microarchitecture, 2014. 609\u2013622","key":"3807_CR7","DOI":"10.1109\/MICRO.2014.58"},{"unstructured":"Hu H, Peng R, Tai Y W, et al. Network trimming: a data-driven neuron pruning approach towards efficient deep architectures. 2016. ArXiv:1607.03250","key":"3807_CR8"},{"unstructured":"Li H, Kadav A, Durdanovic I, et al. Pruning filters for efficient convnets. 2016. ArXiv:1608.08710","key":"3807_CR9"},{"doi-asserted-by":"crossref","unstructured":"Lebedev V, Lempitsky V. Fast convnets using group-wise brain damage. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. 2554\u20132564","key":"3807_CR10","DOI":"10.1109\/CVPR.2016.280"},{"doi-asserted-by":"crossref","unstructured":"He Y H, Zhang X Y, Sun J. Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, 2017. 1389\u20131397","key":"3807_CR11","DOI":"10.1109\/ICCV.2017.155"},{"key":"3807_CR12","doi-asserted-by":"publisher","first-page":"229101","DOI":"10.1007\/s11432-020-3162-4","volume":"65","author":"L H Guo","year":"2022","unstructured":"Guo L H, Chen D W, Jia K. Knowledge transferred adaptive filter pruning for CNN compression and acceleration. Sci China Inf Sci, 2022, 65: 229101","journal-title":"Sci China Inf Sci"},{"doi-asserted-by":"crossref","unstructured":"Choi S, Sim J, Kang M, et al. TrainWare: a memory optimized weight update architecture for on-device convolutional neural network training. In: Proceedings of the International Symposium on Low Power Electronics and Design, 2018. 1\u20136","key":"3807_CR13","DOI":"10.1145\/3218603.3218625"},{"key":"3807_CR14","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1145\/3007787.3001177","volume":"44","author":"Y H Chen","year":"2016","unstructured":"Chen Y H, Emer J, Sze V. Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks. SIGARCH Comput Archit News, 2016, 44: 367\u2013379","journal-title":"SIGARCH Comput Archit News"},{"doi-asserted-by":"crossref","unstructured":"Zhang S J, Du Z D, Zhang L, et al. Cambricon-X: an accelerator for sparse neural networks. In: Proceedings of the 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), 2016. 1\u201312","key":"3807_CR15","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"3807_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3007787.3001138","volume":"44","author":"J Albericio","year":"2016","unstructured":"Albericio J, Judd P, Hetherington T, et al. Cnvlutin: ineffectual-neuron-free deep neural network computing. SIGARCH Comput Archit News, 2016, 44: 1\u201313","journal-title":"SIGARCH Comput Archit News"},{"doi-asserted-by":"crossref","unstructured":"Zhou X D, Du Z D, Guo Q, et al. Cambricon-S: addressing irregularity in sparse neural networks through a cooperative software\/hardware approach. In: Proceedings of the 51st Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), 2018. 15\u201328","key":"3807_CR17","DOI":"10.1109\/MICRO.2018.00011"},{"key":"3807_CR18","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/3140659.3080254","volume":"45","author":"A Parashar","year":"2017","unstructured":"Parashar A, Rhu M, Mukkara A, et al. SCNN: an accelerator for compressed-sparse convolutional neural networks. SIGARCH Comput Archit News, 2017, 45: 27\u201340","journal-title":"SIGARCH Comput Archit News"},{"unstructured":"Tan M, Le Q. EfficientNetV2: smaller models and faster training. 2021. ArXiv:2104.00298","key":"3807_CR19"},{"unstructured":"Howard A, Zhu M, Chen B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications. 2017. ArXiv:1704.04861","key":"3807_CR20"},{"doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, et al. MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. 4510\u20134520","key":"3807_CR21","DOI":"10.1109\/CVPR.2018.00474"},{"doi-asserted-by":"crossref","unstructured":"Gondimalla A, Chesnut N, Thottethodi M, et al. SparTen: a sparse tensor accelerator for convolutional neural networks. In: Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture, 2019. 151\u2013165","key":"3807_CR22","DOI":"10.1145\/3352460.3358291"},{"doi-asserted-by":"crossref","unstructured":"Lee J, Lee J, Han D, et al. 7.7 LNPU: a 25.3 TFLOPS\/W sparse deep-neural-network learning processor with fine-grained mixed precision of FP8-FP16. In: Proceedings of IEEE International Solid-State Circuits Conference (ISSCC), 2019. 142\u2013144","key":"3807_CR23","DOI":"10.1109\/ISSCC.2019.8662302"},{"unstructured":"Jouppi N P, Young C, Patil N, et al. In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture (ISCA), 2017. 1\u201312","key":"3807_CR24"},{"doi-asserted-by":"crossref","unstructured":"He X, Pal S, Amarnath A, et al. Sparse-TPU: adapting systolic arrays for sparse matrices. In: Proceedings of the 34th ACM International Conference on Supercomputing, 2020. 1\u201312","key":"3807_CR25","DOI":"10.1145\/3392717.3392751"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-022-3807-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-022-3807-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-022-3807-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T02:18:50Z","timestamp":1742696330000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-022-3807-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,23]]},"references-count":25,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["3807"],"URL":"https:\/\/doi.org\/10.1007\/s11432-022-3807-9","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"type":"print","value":"1674-733X"},{"type":"electronic","value":"1869-1919"}],"subject":[],"published":{"date-parts":[[2024,1,23]]},"assertion":[{"value":"31 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 December 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"122405"}}