{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T09:14:17Z","timestamp":1765012457121,"version":"3.46.0"},"reference-count":56,"publisher":"Wiley","issue":"27-28","license":[{"start":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T00:00:00Z","timestamp":1762041600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2025,12,25]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Spiking neural networks (SNNs) have gained significant attention due to their energy\u2010efficient and multiplication\u2010free characteristics. Despite these advantages, deploying large\u2010scale SNNs on edge hardware is challenging due to limited resource availability. Network pruning offers a viable approach to compress the network scale and reduce hardware resource requirements for model deployment. However, existing SNN pruning methods cause high pruning costs and performance loss because they lack efficiency in processing the sparse spike representation of SNNs. In this paper, inspired by the critical brain hypothesis in neuroscience and the high biological plausibility of SNNs, we explore and leverage criticality to facilitate efficient pruning in deep SNNs. We first explain criticality in SNNs from the perspective of maximizing feature information entropy. Second, we propose a low\u2010cost metric to assess neuron criticality in feature transmission and design a pruning\u2010regeneration method that incorporates this criticality into the pruning process. Experimental results demonstrate that our method achieves higher performance than the current state\u2010of\u2010the\u2010art (SOTA) method with up to 95.26% reduction in pruning cost. The criticality\u2010based regeneration process efficiently selects potential structures and facilitates consistent feature representation. Our code is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/MmPple\/pruning-criticality\">https:\/\/github.com\/MmPple\/pruning\u2010criticality<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1002\/cpe.70404","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T02:44:50Z","timestamp":1762137890000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Brain\u2010Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks"],"prefix":"10.1002","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7616-4453","authenticated-orcid":false,"given":"Shuo","family":"Chen","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Science  Beijing China"},{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences  Beijing China"}]},{"given":"Zeshi","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Science  Beijing China"}]},{"given":"Haihang","family":"You","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Science  Beijing China"}]}],"member":"311","published-online":{"date-parts":[[2025,11,2]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011311"},{"key":"e_1_2_10_3_1","first-page":"11062","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Zheng H.","year":"2021"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(97)00011-7"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2015.2474396"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.112130359"},{"key":"e_1_2_10_7_1","first-page":"614","volume-title":"2023 56th IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Liu Z.","year":"2023"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1424-8"},{"key":"e_1_2_10_9_1","first-page":"3953","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","author":"Kundu S.","year":"2021"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1004485"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_7"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3109064"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/236"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611838"},{"key":"e_1_2_10_15_1","first-page":"1","volume-title":"2023 60th ACM\/IEEE Design Automation Conference (DAC)","author":"Huang S.","year":"2023"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26002"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586323"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-6710-5_3"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2007.2092"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2012.00163"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/nphys289"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3864-09.2009"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.88.062717"},{"key":"e_1_2_10_24_1","first-page":"1135","article-title":"Learning Both Weights and Connections for Efficient Neural Network","volume":"28","author":"Han S.","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_25_1","first-page":"9908","article-title":"Sparse Training via Boosting Pruning Plasticity With Neuroregeneration","volume":"34","author":"Liu S.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_26_1","article-title":"To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression","author":"Zhu M.","year":"2017","journal-title":"arXiv"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_2_10_28_1","article-title":"Pruning Convolutional Neural Networks for Resource Efficient Inference","author":"Molchanov P.","year":"2016","journal-title":"arXiv"},{"key":"e_1_2_10_29_1","article-title":"Network Trimming: A Data\u2010Driven Neuron Pruning Approach Towards Efficient Deep Architectures","author":"Hu H.","year":"2016","journal-title":"arXiv"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2025.1545583"},{"key":"e_1_2_10_31_1","first-page":"795","article-title":"Long Short\u2010Term Memory and Learning\u2010to\u2010Learn in Networks of Spiking Neurons","volume":"31","author":"Bellec G.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00331"},{"key":"e_1_2_10_33_1","first-page":"E1356","article-title":"Landau\u2013Ginzburg Theory of Cortex Dynamics: Scale\u2010Free Avalanches Emerge at the Edge of Synchronization","volume":"115","author":"Di Santo S.","year":"2018","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2021.611183"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnsys.2014.00166"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.75.1222"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015835"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2014.2310593"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2258"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.7770778"},{"volume-title":"Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems","year":"2001","author":"Dayan P.","key":"e_1_2_10_41_1"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815706"},{"volume-title":"Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems","year":"2005","author":"Dayan P.","key":"e_1_2_10_43_1"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"e_1_2_10_45_1","article-title":"Very Deep Convolutional Networks for Large\u2010Scale Image Recognition","author":"Simonyan K.","year":"2014","journal-title":"arXiv"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_10_47_1","unstructured":"A.Krizhevsky \u201cLearning Multiple Layers of Features from Tiny Images Technical Report University of Toronto \u201d(2009) https:\/\/www.cs.toronto.edu\/\u223ckriz\/learning\u2010features\u20102009\u2010TR.pdf."},{"key":"e_1_2_10_48_1","unstructured":"Y.LeandX.Yang \u201cTiny ImageNet Visual Recognition Challenge \u201dStanford University (CS231n) (2015) http:\/\/tiny\u2010imagenet.herokuapp.com\/."},{"key":"e_1_2_10_49_1","first-page":"3701","volume-title":"International Conference on Machine Learning","author":"Chen Y.","year":"2022"},{"key":"e_1_2_10_50_1","first-page":"2943","volume-title":"International Conference on Machine Learning","author":"Evci U.","year":"2020"},{"volume-title":"International Conference on Learning Representations (ICLR)","year":"2021","author":"Wang H.","key":"e_1_2_10_51_1"},{"key":"e_1_2_10_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-9473(01)00040-8"},{"key":"e_1_2_10_53_1","first-page":"42","article-title":"New k\u2010Means Clustering Methods That Minimize the Total Intra\u2010Cluster Variance","volume":"3","author":"Oti E. U.","year":"2020","journal-title":"African Journal of Mathematical Statistics"},{"key":"e_1_2_10_54_1","first-page":"125","article-title":"Adversarial Examples Are Not Bugs, They Are Features","volume":"32","author":"Ilyas A.","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_55_1","first-page":"78","volume-title":"Proceedings of the Twenty\u2010First International Conference on Machine Learning","author":"Ng A. Y.","year":"2004"},{"key":"e_1_2_10_56_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"e_1_2_10_57_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T09:11:07Z","timestamp":1765012267000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70404"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,2]]},"references-count":56,"journal-issue":{"issue":"27-28","published-print":{"date-parts":[[2025,12,25]]}},"alternative-id":["10.1002\/cpe.70404"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70404","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"type":"print","value":"1532-0626"},{"type":"electronic","value":"1532-0634"}],"subject":[],"published":{"date-parts":[[2025,11,2]]},"assertion":[{"value":"2025-04-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70404"}}