{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:40:46Z","timestamp":1781797246867,"version":"3.54.5"},"reference-count":42,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2022,1,22]],"date-time":"2022-01-22T00:00:00Z","timestamp":1642809600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61975124"],"award-info":[{"award-number":["61975124"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100007219","name":"Shanghai Natural Science Foundation","doi-asserted-by":"crossref","award":["20ZR1438500"],"award-info":[{"award-number":["20ZR1438500"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Open Project Program of Shanghai Key Laboratory of Data Science","award":["2020090600003"],"award-info":[{"award-number":["2020090600003"]}]},{"name":"State Key Lab of Computer Architecture, ICT, CAS","award":["CARCHA202111"],"award-info":[{"award-number":["CARCHA202111"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Internet Technol."],"published-print":{"date-parts":[[2022,8,31]]},"abstract":"<jats:p>Convolutional Neural Networks (CNNs) and deep learning technology are applied in current financial market to rapidly promote the development of finance market and Internet economy. The continuous development of neural networks with more hidden layers improves the performance but increases the computational complexity. Generally, channel pruning methods are useful to compact neural networks. However, typical channel pruning methods would remove layers by mistake due to the static pruning ratio of manual setting, which could destroy the whole structure of neural networks. It is difficult to improve the ratio of compressing neural networks only by pruning channels while maintaining good network structures.<\/jats:p>\n          <jats:p>\n            Therefore, we propose a novel neural Networks Pruning by Recurrent Weights (\n            <jats:italic>NPRW<\/jats:italic>\n            ) that can repeatedly evaluate the significance of weights and adaptively adjust them to compress neural networks within acceptable loss of accuracy. The recurrent weights with low sensitivity are compulsorily set to zero by evaluating the magnitude of weights, and pruned network only uses a few significant weights. Then, we add the regularization to the scaling factors on neural networks, in which recurrent weights with high sensitivity can be dynamically updated and weights of low sensitivity stay at zero invariably. By this way, the significance of channels can be quantitatively evaluated by recurrent weights. It has been verified with typical neural networks of LeNet, VGGNet, and ResNet on multiple benchmark datasets involving stock index futures, digital recognition, and image classification. The pruned LeNet-5 achieves the 58.9% reduction amount of parameters with 0.29% loss of total accuracy for Shanghai and Shenzhen 300 stock index futures. As for the CIFAR-10, the pruned VGG-19 reduces more than 50% FLOPs, and the decrease of network accuracy is less than 0.5%. In addition, the pruned ResNet-164 tested on the SVHN reduces more than 58% FLOPs with relative improvement on accuracy by 0.11%.\n          <\/jats:p>","DOI":"10.1145\/3433547","type":"journal-article","created":{"date-parts":[[2022,1,23]],"date-time":"2022-01-23T06:39:00Z","timestamp":1642919940000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Neural Network Pruning by Recurrent Weights for Finance Market"],"prefix":"10.1145","volume":"22","author":[{"given":"Songwen","family":"Pei","sequence":"first","affiliation":[{"name":"University of Shanghai for Science and Technology, and ICT, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusheng","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science &amp; Engineering, University of Shanghaifor Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Economics, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1004-0140","authenticated-orcid":false,"given":"Meikang","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Texas A&amp;M University-Commerce, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,1,22]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374354"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2019.112630"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.08.024"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2018.07.008"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.09.092"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2019.112707"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1700202"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CBI.2017.23"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00490"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969505"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2018.00056"},{"key":"e_1_3_1_15_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Ye Jianbo","year":"2018","unstructured":"Jianbo Ye, Xin Lu, Zhe Lin, and James Z. Wang. 2018. Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers. In Proceedings of the International Conference on Learning Representations (ICLR). 1\u201311. DOI:1802.00124"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.11.040"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999852"},{"key":"e_1_3_1_21_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Li Hao","year":"2016","unstructured":"Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2016. Pruning filters for efficient ConvNets. In Proceedings of the International Conference on Learning Representations (ICLR). 1\u201313. DOI:1608.08710"},{"key":"e_1_3_1_22_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Hu Hengyuan","year":"2017","unstructured":"Hengyuan Hu, Rui Peng, Yu-Wing Tai, and Chi-Keung Tang. 2017. Network trimming: A data-driven neuron pruning approach towards efficient deep architectures. In Proceedings of the International Conference on Learning Representations (ICLR). 1\u20139. DOI:1607.03250"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157329"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157350"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3327025"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969366"},{"key":"e_1_3_1_28_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and W. J. Dally. 2016. Compressing deep neural networks with pruning trained quantization and Huffman coding. In Proceedings of the International Conference on Learning Representations (ICLR). 1\u201314. DOI:1510.00149"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60239-0_12"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.5555\/2968826.2968968"},{"key":"e_1_3_1_31_2","first-page":"1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang Min","year":"2016","unstructured":"Min Wang, Baoyuan Liu, and Hassan Foroosh. 2016. Design of efficient convolutional layers using single intra-channel convolution, topological subdivisioning and spatial \u201cbottleneck\u201d structure. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1\u20139. DOI:1608.04337"},{"key":"e_1_3_1_32_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Hou Lu","year":"2018","unstructured":"Lu Hou and James T. Kwok. 2018. Loss-aware weight quantization of deep networks. In Proceedings of the International Conference on Learning Representations (ICLR). 1\u201316. DOI:1802.08635"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045361"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/1497561.1497568"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2015.2398824"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.02.002"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/72.248452"},{"key":"e_1_3_1_41_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proceedings of the International Conference on Learning Representations (ICLR). 1\u201314. DOI:1409.1556"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"}],"container-title":["ACM Transactions on Internet Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3433547","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3433547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:10Z","timestamp":1750195690000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3433547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,22]]},"references-count":42,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,8,31]]}},"alternative-id":["10.1145\/3433547"],"URL":"https:\/\/doi.org\/10.1145\/3433547","relation":{},"ISSN":["1533-5399","1557-6051"],"issn-type":[{"value":"1533-5399","type":"print"},{"value":"1557-6051","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,22]]},"assertion":[{"value":"2020-08-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}