{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:44:35Z","timestamp":1767325475100,"version":"3.48.0"},"reference-count":50,"publisher":"World Scientific Pub Co Pte Ltd","issue":"02","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62376127"],"award-info":[{"award-number":["62376127"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61876089"],"award-info":[{"award-number":["61876089"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61876185"],"award-info":[{"award-number":["61876185"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61902281"],"award-info":[{"award-number":["61902281"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61403206"],"award-info":[{"award-number":["61403206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"crossref","award":["BK20141005"],"award-info":[{"award-number":["BK20141005"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Natural Science Foundation of the Jiangsu Higher Education Institutions of China","award":["14KJB520025"],"award-info":[{"award-number":["14KJB520025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Neur. Syst."],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:p>Generative Adversarial Networks (GANs) have demonstrated remarkable success in high-quality image synthesis, with StyleGAN and its successor, StyleGAN2, achieving state-of-the-art performance in terms of realism and control over generated features. However, the large number of parameters and high floating-point operations per second (FLOPs) hinder real-time applications and scalability, posing challenges for deploying these models in resource-constrained environments such as edge devices and mobile platforms. To address this issue, we propose Evolutionary Channel Pruning for StyleGANs (ECP-StyleGANs), a novel algorithm that leverages evolutionary algorithms to compress StyleGAN and StyleGAN2 while maintaining competitive image quality. Our approach encodes pruning configurations as binary masks on the model\u2019s convolutional channels and iteratively refines them through selection, crossover, and mutation. By integrating carefully designed fitness functions that balance model complexity and generation quality, ECP-StyleGANs identifies optimally pruned architectures that reduce computational demands without compromising visual fidelity, achieving approximately a 4 \u00d7 reduction in FLOPs and parameters, while maintaining visual fidelity with only a slight increase in FID (Fr\u00e9chet Inception Distance) compared to the original un-pruned model. This study should be interpreted as a preliminary step towards the formulation and management of the generative AI pruning problem as a multi-objective optimisation task, aimed at enhancing the trade-off between model efficiency and image quality, thereby making large deep models more accessible for real-world applications such as edge devices and resource-constrained environments. Source codes will be available.<\/jats:p>","DOI":"10.1142\/s0129065725500704","type":"journal-article","created":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T04:15:47Z","timestamp":1757132147000},"source":"Crossref","is-referenced-by-count":0,"title":["Evolutionary Channel Pruning for Style-Based Generative Adversarial Networks"],"prefix":"10.1142","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0064-7002","authenticated-orcid":false,"given":"Yixia","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Electronic Engineering, University of Surrey, Guildford, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6100-6532","authenticated-orcid":false,"given":"Ferrante","family":"Neri","sequence":"additional","affiliation":[{"name":"School of Computer Science and Electronic Engineering, University of Surrey, Guildford, United Kingdom"},{"name":"School of Software, Nanjing University of Information Science and Technology, Nanjing, P.\u00a0R.\u00a0China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0926-4454","authenticated-orcid":false,"given":"Xilu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Electronic Engineering, University of Surrey, Guildford, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9625-697X","authenticated-orcid":false,"given":"Pengcheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Software, Nanjing University of Information Science and Technology, Nanjing, P.\u00a0R.\u00a0China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9069-7547","authenticated-orcid":false,"given":"Yu","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Software, Nanjing University of Information Science and Technology, Nanjing, P.\u00a0R.\u00a0China"}]}],"member":"219","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"S0129065725500704BIB001","first-page":"2672","volume":"27","author":"Goodfellow I.","year":"2014","journal-title":"Adv Neural Inf Process Syst."},{"key":"S0129065725500704BIB002","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065724500321"},{"key":"S0129065725500704BIB003","doi-asserted-by":"publisher","DOI":"10.1111\/mice.13116"},{"key":"S0129065725500704BIB004","doi-asserted-by":"publisher","DOI":"10.1111\/mice.13119"},{"key":"S0129065725500704BIB005","doi-asserted-by":"publisher","DOI":"10.1111\/mice.13231"},{"key":"S0129065725500704BIB006","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad1f77"},{"key":"S0129065725500704BIB007","first-page":"1","volume-title":"Proc. 6th Int. Conf. Communication and Electronics Systems","author":"Durgadevi M.","year":"2021"},{"journal-title":"Trans. Mach. Learn. Res.","year":"2024","author":"Gao W.","key":"S0129065725500704BIB008"},{"key":"S0129065725500704BIB009","doi-asserted-by":"crossref","unstructured":"T. Karras, A style-based generator architecture for generative adversarial networks, preprint (2019), arXiv:1812.04948.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"S0129065725500704BIB010","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"S0129065725500704BIB011","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3350004"},{"key":"S0129065725500704BIB012","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC55196.2022.9952574"},{"key":"S0129065725500704BIB013","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3447085"},{"key":"S0129065725500704BIB014","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04359-7"},{"key":"S0129065725500704BIB015","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3334614"},{"key":"S0129065725500704BIB016","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"S0129065725500704BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"S0129065725500704BIB018","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00755"},{"key":"S0129065725500704BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01198"},{"key":"S0129065725500704BIB020","doi-asserted-by":"crossref","unstructured":"S. Wu, H. Du, Y. Xiong, S. Chen, T.W. Kuo, N. Guan and C. J. Xue, EvoP: Robust LLM inference via evolutionary pruning, preprint (2025), arXiv:2502. 14910.","DOI":"10.1007\/978-981-95-3343-5_36"},{"key":"S0129065725500704BIB021","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110229"},{"key":"S0129065725500704BIB022","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065723500168"},{"key":"S0129065725500704BIB023","doi-asserted-by":"publisher","DOI":"10.1145\/1096601.1096632"},{"key":"S0129065725500704BIB024","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-9445(1995)121:11(1588)"},{"key":"S0129065725500704BIB025","doi-asserted-by":"publisher","DOI":"10.1080\/03052150108940930"},{"key":"S0129065725500704BIB026","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.01.010"},{"key":"S0129065725500704BIB027","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_2"},{"key":"S0129065725500704BIB028","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2023.3338371"},{"key":"S0129065725500704BIB029","doi-asserted-by":"publisher","DOI":"10.18178\/ijmlc.2017.7.1.611"},{"key":"S0129065725500704BIB030","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88908-3_9"},{"key":"S0129065725500704BIB031","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-003-0328-5"},{"key":"S0129065725500704BIB032","first-page":"6626","volume":"30","author":"Heusel M.","year":"2017","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"S0129065725500704BIB033","doi-asserted-by":"publisher","DOI":"10.1007\/s00158-017-1835-9"},{"key":"S0129065725500704BIB034","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12255"},{"key":"S0129065725500704BIB035","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2011.12.004"},{"key":"S0129065725500704BIB036","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2003.814633"},{"key":"S0129065725500704BIB037","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.227"},{"key":"S0129065725500704BIB038","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"S0129065725500704BIB039","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2933032"},{"key":"S0129065725500704BIB040","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00029"},{"key":"S0129065725500704BIB041","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_25"},{"key":"S0129065725500704BIB042","unstructured":"B. Liu, Y. Zhu, K. Song and A. Elgammal, Towards faster and stabilized GAN training for high-fidelity few-shot image synthesis, preprint (2021), arXiv:2101.04775."},{"key":"S0129065725500704BIB043","first-page":"1","volume":"41","author":"Tian Y.","year":"2024","journal-title":"Vis. Comput."},{"key":"S0129065725500704BIB044","doi-asserted-by":"publisher","DOI":"10.1145\/3453474"},{"key":"S0129065725500704BIB045","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"S0129065725500704BIB046","unstructured":"W. Wang, W. Chen, Y. Luo, Y. Long, Z. Lin, L. Zhang, B. Lin, D. Cai and X. He, Model compression and efficient inference for large language models: A survey, preprint (2024), arXiv:2402.09748."},{"key":"S0129065725500704BIB047","doi-asserted-by":"publisher","DOI":"10.1145\/3524495"},{"key":"S0129065725500704BIB048","doi-asserted-by":"publisher","DOI":"10.1145\/3657282"},{"key":"S0129065725500704BIB049","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"S0129065725500704BIB050","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065725500133"}],"container-title":["International Journal of Neural Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0129065725500704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:40:42Z","timestamp":1767325242000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0129065725500704"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":50,"journal-issue":{"issue":"02","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1142\/S0129065725500704"],"URL":"https:\/\/doi.org\/10.1142\/s0129065725500704","relation":{},"ISSN":["0129-0657","1793-6462"],"issn-type":[{"type":"print","value":"0129-0657"},{"type":"electronic","value":"1793-6462"}],"subject":[],"published":{"date-parts":[[2025,9,27]]},"article-number":"2550070"}}