{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:40:23Z","timestamp":1785606023425,"version":"3.56.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100006692","name":"Universit\u00e0 degli Studi di Torino","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006692","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Telecommun Syst"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s11235-025-01363-2","type":"journal-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T09:52:35Z","timestamp":1761385955000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["TinyML model compression: A comparative study of pruning and quantization on selected standard and custom neural networks"],"prefix":"10.1007","volume":"88","author":[{"given":"Muhammad Yasir","family":"Shabir","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gianluca","family":"Torta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ferruccio","family":"Damiani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,25]]},"reference":[{"issue":"3","key":"1363_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3595633","volume":"23","author":"H-A Rashid","year":"2024","unstructured":"Rashid, H.-A., Kallakuri, U., & Mohsenin, T. (2024). Tinym2net-v2: A compact low-power software hardware architecture for multimodal deep neural networks. ACM Transactions on Embedded Computing Systems, 23(3), 1\u201323.","journal-title":"ACM Transactions on Embedded Computing Systems"},{"issue":"14","key":"1363_CR2","doi-asserted-by":"publisher","first-page":"3245","DOI":"10.3390\/math11143245","volume":"11","author":"M Irshad","year":"2023","unstructured":"Irshad, M., Yasmin, M., Sharif, M. I., Rashid, M., Sharif, M. I., & Kadry, S. (2023). A novel light u-net model for left ventricle segmentation using mri. Mathematics, 11(14), 3245.","journal-title":"Mathematics"},{"key":"1363_CR3","doi-asserted-by":"crossref","unstructured":"Islam, M. M., & Alawad, M. (2023). Stochastically pruning large language models using sparsity regularization and compressive sensing. In: Proceedings of the Great Lakes Symposium on VLSI 2023, pp. 63\u201368","DOI":"10.1145\/3583781.3590232"},{"issue":"3","key":"1363_CR4","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MCAS.2023.3302182","volume":"23","author":"J Lin","year":"2023","unstructured":"Lin, J., Zhu, L., Chen, W.-M., Wang, W.-C., & Han, S. (2023). Tiny machine learning: progress and futures [feature]. IEEE Circuits and Systems Magazine, 23(3), 8\u201334.","journal-title":"IEEE Circuits and Systems Magazine"},{"key":"1363_CR5","first-page":"483","volume":"6","author":"H Shen","year":"2024","unstructured":"Shen, H., Mellempudi, N., He, X., Gao, Q., Wang, C., & Wang, M. (2024). Efficient post-training quantization with fp8 formats. Proceedings of Machine Learning and Systems, 6, 483\u2013498.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"1363_CR6","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., & Graf, H. P. (2016). Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710"},{"key":"1363_CR7","unstructured":"Frankle, J., & Carbin, M. (2018). The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635"},{"key":"1363_CR8","doi-asserted-by":"crossref","unstructured":"Fang, G., Ma, X., Song, M., Mi, M. B., & Wang, X. (2023). Depgraph: Towards any structural pruning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16091\u201316101","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"1363_CR9","doi-asserted-by":"crossref","unstructured":"Ding, X., Hao, T., Tan, J., Liu, J., Han, J., Guo, Y., & Ding, G. (2021). Resrep: Lossless cnn pruning via decoupling remembering and forgetting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4510\u20134520","DOI":"10.1109\/ICCV48922.2021.00447"},{"key":"1363_CR10","unstructured":"Wang, H., Qin, C., Zhang, Y., & Fu, Y. (2020). Neural pruning via growing regularization. arXiv preprint arXiv:2012.09243"},{"key":"1363_CR11","first-page":"18098","volume":"33","author":"SP Singh","year":"2020","unstructured":"Singh, S. P., & Alistarh, D. (2020). Woodfisher: Efficient second-order approximation for neural network compression. Advances in Neural Information Processing Systems, 33, 18098\u201318109.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1363_CR12","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., & Sun, J. (2017). Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1389\u20131397","DOI":"10.1109\/ICCV.2017.155"},{"key":"1363_CR13","doi-asserted-by":"crossref","unstructured":"Mohanty, L., Kumar, A., Mehta, V., Agarwal, M., & Suri, J. S. (2024). Pruning techniques for artificial intelligence networks: a deeper look at their engineering design and bias: the first review of its kind. Multimedia Tools and Applications, 1\u201375","DOI":"10.1007\/s11042-024-19192-x"},{"key":"1363_CR14","unstructured":"Siegel, J. W., Chen, J., Zhang, P., & Xu, J. (2020). Training sparse neural networks using compressed sensing. arXiv preprint arXiv:2008.09661"},{"key":"1363_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107988","volume":"239","author":"G Lee","year":"2022","unstructured":"Lee, G., & Lee, K. (2022). Dnn compression by admm-based joint pruning. Knowledge-Based Systems, 239, Article 107988.","journal-title":"Knowledge-Based Systems"},{"issue":"1","key":"1363_CR16","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/s44196-023-00279-6","volume":"16","author":"I Al-Shourbaji","year":"2023","unstructured":"Al-Shourbaji, I., Kachare, P., Fadlelseed, S., Jabbari, A., Hussien, A. G., Al-Saqqar, F., Abualigah, L., & Alameen, A. (2023). Artificial ecosystem-based optimization with dwarf mongoose optimization for feature selection and global optimization problems. International Journal of Computational Intelligence Systems, 16(1), 102.","journal-title":"International Journal of Computational Intelligence Systems"},{"issue":"5","key":"1363_CR17","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.1007\/s10994-024-06516-z","volume":"113","author":"A Dekhovich","year":"2024","unstructured":"Dekhovich, A., Tax, D. M., Sluiter, M. H., & Bessa, M. A. (2024). Neural network relief: a pruning algorithm based on neural activity. Machine Learning, 113(5), 2597\u20132618.","journal-title":"Machine Learning"},{"key":"1363_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106496","volume":"179","author":"Y Lian","year":"2024","unstructured":"Lian, Y., Peng, P., Jiang, K., & Xu, W. (2024). Cross-layer importance evaluation for neural network pruning. Neural Networks, 179, Article 106496.","journal-title":"Neural Networks"},{"key":"1363_CR19","unstructured":"Lubana, E. S., & Dick, R. P. (2020). A gradient flow framework for analyzing network pruning. arXiv preprint arXiv:2009.11839"},{"key":"1363_CR20","doi-asserted-by":"crossref","unstructured":"Gao, S., Li, J., Zhang, Z., Zhang, Y., Cai, W., & Huang, H. (2024). Device-wise federated network pruning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12342\u201312352","DOI":"10.1109\/CVPR52733.2024.01173"},{"key":"1363_CR21","unstructured":"TensorFlow Model Optimization Team: TensorFlow Model Optimization Toolkit: Pruning. https:\/\/www.tensorflow.org\/model_optimization\/guide\/pruning. Accessed: 2025-09-06 (2020)"},{"key":"1363_CR22","unstructured":"Zhu, M., & Gupta, S. (2017). To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878"},{"key":"1363_CR23","unstructured":"Azarian, K., Bhalgat, Y., Lee, J., & Blankevoort, T. (2020). Learned threshold pruning. arXiv preprint arXiv:2003.00075"},{"key":"1363_CR24","first-page":"2383","volume":"330","author":"G Li","year":"2018","unstructured":"Li, G., Qian, C., Jiang, C., Lu, X., & Tang, K. (2018). Optimization based layer-wise magnitude-based pruning for dnn compression. IJCAI, 330, 2383\u20132389.","journal-title":"IJCAI"},{"key":"1363_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2025.105002","volume":"159","author":"J Xiang","year":"2025","unstructured":"Xiang, J., Song, T., & Liu, W. (2025). Fnat-net: Feature space-based compression-aware adaptive thresholding network. Digital Signal Processing, 159, Article 105002.","journal-title":"Digital Signal Processing"},{"issue":"6","key":"1363_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3623402","volume":"14","author":"B Rokh","year":"2023","unstructured":"Rokh, B., Azarpeyvand, A., & Khanteymoori, A. (2023). A comprehensive survey on model quantization for deep neural networks in image classification. ACM Transactions on Intelligent Systems and Technology, 14(6), 1\u201350.","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"1363_CR27","doi-asserted-by":"crossref","unstructured":"Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., & Kalenichenko, D.(2018). Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704\u20132713","DOI":"10.1109\/CVPR.2018.00286"},{"key":"1363_CR28","unstructured":"Banner, R., Hubara, I., Hoffer, E., & Soudry, D. (2018). Scalable methods for 8-bit training of neural networks. Advances in neural information processing systems 31"},{"key":"1363_CR29","unstructured":"Banner, R., Nahshan, Y., & Soudry, D. (2019). Post training 4-bit quantization of convolutional networks for rapid-deployment. Advances in Neural Information Processing Systems 32"},{"key":"1363_CR30","doi-asserted-by":"crossref","unstructured":"Cai, H., Wang, T., Wu, Z., Wang, K., Lin, J., & Han, S. (2019). On-device image classification with proxyless neural architecture search and quantization-aware fine-tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 0\u20130","DOI":"10.1109\/ICCVW.2019.00307"},{"key":"1363_CR31","unstructured":"Yao, Z., Dong, Z., Zheng, Z., Gholami, A., Yu, J., Tan, E., Wang, L., Huang, Q., Wang, Y., Mahoney, M., et al. (2021). Hawq-v3: Dyadic neural network quantization. In: International Conference on Machine Learning, pp. 11875\u201311886 . PMLR"},{"key":"1363_CR32","doi-asserted-by":"crossref","unstructured":"Kwon, S.J., Lee, D., Kim, B., Kapoor, P., Park, B., & Wei, G.-Y. (2020). Structured compression by weight encryption for unstructured pruning and quantization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1909\u20131918","DOI":"10.1109\/CVPR42600.2020.00198"},{"key":"1363_CR33","doi-asserted-by":"publisher","first-page":"26419","DOI":"10.1109\/ACCESS.2023.3257864","volume":"11","author":"J Kim","year":"2023","unstructured":"Kim, J. (2023). Quantization robust pruning with knowledge distillation. IEEE Access, 11, 26419\u201326426.","journal-title":"IEEE Access"},{"key":"1363_CR34","doi-asserted-by":"crossref","unstructured":"Kallakuri, U., Humes, E., & Mohsenin, T. (2024). Resource-aware saliency-guided differentiable pruning for deep neural networks. In: Proceedings of the Great Lakes Symposium on VLSI 2024, pp. 694\u2013699","DOI":"10.1145\/3649476.3658699"},{"key":"1363_CR35","unstructured":"Han, S., Mao, H., & Dally, W. J. (2015). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149"},{"key":"1363_CR36","unstructured":"Wang, Z., Liu, X., Huang, L., Chen, Y., Zhang, Y., Lin, Z., & Wang, R. (2021). Model pruning based on quantified similarity of feature maps. arXiv preprint arXiv:2105.06052"},{"key":"1363_CR37","doi-asserted-by":"crossref","unstructured":"Paupamah, K., James, S., & Klein, R. (2020). Quantisation and pruning for neural network compression and regularisation. In: 2020 International SAUPEC\/RobMech\/PRASA Conference, pp. 1\u20136 . IEEE","DOI":"10.1109\/SAUPEC\/RobMech\/PRASA48453.2020.9041096"},{"key":"1363_CR38","unstructured":"Zandonati, B., Bucagu, G., Pol, A. A., Pierini, M., Sirkin, O., & Kopetz, T. (2023). Towards optimal compression: Joint pruning and quantization. arXiv preprint arXiv:2302.07612"},{"key":"1363_CR39","doi-asserted-by":"crossref","unstructured":"Rashid, M., Amparore, E. G., Ferrari, E., & Verda, D. (2024). Using stratified sampling to improve lime image explanations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 14785\u201314792","DOI":"10.1609\/aaai.v38i13.29397"},{"issue":"1","key":"1363_CR40","doi-asserted-by":"publisher","first-page":"19749","DOI":"10.48084\/etasr.9441","volume":"15","author":"N Alshammry","year":"2025","unstructured":"Alshammry, N., Saidani, T., Albalawi, N. S., Alenezi, S. M., Alhamazani, F., Alshammari, S. A., Aleinzi, M., Alanazi, A., & Elsayed, M. S. (2025). Q_yolov5m: A quantization-based approach for accelerating object detection on embedded platforms. Engineering, Technology & Applied Science Research, 15(1), 19749\u201319755.","journal-title":"Engineering, Technology & Applied Science Research"},{"key":"1363_CR41","unstructured":"Song, J., & Lin, F. (2025). Splitquant: Layer splitting for low-bit neural network quantization. arXiv preprint arXiv:2501.12428"},{"key":"1363_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2024.111142","volume":"238","author":"H Liu","year":"2025","unstructured":"Liu, H., Niu, B., Liu, Z., Li, M., & Shi, Z. (2025). Transformer fault diagnosis method based on the three-stage lightweight residual neural network. Electric Power Systems Research, 238, Article 111142.","journal-title":"Electric Power Systems Research"},{"key":"1363_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106910","volume":"182","author":"Z Huang","year":"2025","unstructured":"Huang, Z., Han, X., Yu, Z., Zhao, Y., Hou, M., & Hu, S. (2025). Hessian-based mixed-precision quantization with transition aware training for neural networks. Neural Networks, 182, Article 106910.","journal-title":"Neural Networks"},{"key":"1363_CR44","unstructured":"Le, K. N., Sato, R., Nakashima, D., Suzuki, T., & Le\u00a0Nguyen, M. (2025). Optiprune: Effective pruning approach for every target sparsity. In: Proceedings of the 31st International Conference on Computational Linguistics, pp. 3600\u20133612"},{"key":"1363_CR45","unstructured":"Abnar, S., Shah, H., Busbridge, D., Ali, A. M. E., Susskind, J., & Thilak, V. (2025). Parameters vs flops: Scaling laws for optimal sparsity for mixture-of-experts language models. arXiv preprint arXiv:2501.12370"},{"key":"1363_CR46","doi-asserted-by":"crossref","unstructured":"He, Y., & Xiao, L. (2023). Structured pruning for deep convolutional neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence","DOI":"10.1109\/TPAMI.2023.3334614"},{"key":"1363_CR47","doi-asserted-by":"crossref","unstructured":"Mao, J., Shen, Y., Guo, J., Yao, Y., Hua, X., & Shen, H. (2025). Prune and merge: Efficient token compression for vision transformer with spatial information preserved. IEEE Transactions on Multimedia","DOI":"10.1109\/TMM.2025.3535405"},{"key":"1363_CR48","first-page":"9908","volume":"34","author":"S Liu","year":"2021","unstructured":"Liu, S., Chen, T., Chen, X., Atashgahi, Z., Yin, L., Kou, H., Shen, L., Pechenizkiy, M., Wang, Z., & Mocanu, D. C. (2021). Sparse training via boosting pruning plasticity with neuroregeneration. Advances in Neural Information Processing Systems, 34, 9908\u20139922.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1363_CR49","unstructured":"Anh, L. T. (2024). CNN-CIFAR-100. Accessed: 2024-10-03 . https:\/\/github.com\/LeoTungAnh\/CNN-CIFAR-100"},{"issue":"9","key":"1363_CR50","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1111\/2041-210X.13652","volume":"12","author":"JW Jolles","year":"2021","unstructured":"Jolles, J. W. (2021). Broad-scale applications of the raspberry pi: A review and guide for biologists. Methods in Ecology and Evolution, 12(9), 1562\u20131579.","journal-title":"Methods in Ecology and Evolution"}],"container-title":["Telecommunication Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11235-025-01363-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11235-025-01363-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11235-025-01363-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:03:13Z","timestamp":1767204193000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11235-025-01363-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,25]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["1363"],"URL":"https:\/\/doi.org\/10.1007\/s11235-025-01363-2","relation":{},"ISSN":["1018-4864","1572-9451"],"issn-type":[{"value":"1018-4864","type":"print"},{"value":"1572-9451","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,25]]},"assertion":[{"value":"11 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"132"}}