{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:48:51Z","timestamp":1782312531290,"version":"3.54.5"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032061058","type":"print"},{"value":"9783032061065","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-06106-5_19","type":"book-chapter","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T10:08:35Z","timestamp":1759399715000},"page":"322-339","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Projective Pruning for\u00a0Decoupling Weights"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3107-7680","authenticated-orcid":false,"given":"Tommy","family":"Chu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7194-1874","authenticated-orcid":false,"given":"Alexander","family":"Kovalenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"19_CR1","unstructured":"Ashkboos, S., Croci, M.L., do\u00a0Nascimento, M.G., Hoefler, T., Hensman, J.: Slicegpt: compress large language models by deleting rows and columns (2024)"},{"key":"19_CR2","unstructured":"Bommasani, R., et\u00a0al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"19_CR3","unstructured":"Cai, H., Gan, C., Wang, T., Zhang, Z., Han, S.: Once-for-all: train one network and specialize it for efficient deployment. In: International Conference on Learning Representations (2020)"},{"key":"19_CR4","unstructured":"Cheng, H., Zhang, M., Shi, J.Q.: A survey on deep neural network pruning: taxonomy, comparison, analysis, and recommendations. In: IEEE Transactions on Pattern Analysis and Machine Intelligence pp. 1\u201320 (2024)"},{"key":"19_CR5","unstructured":"Cottier, B., Rahman, R., Fattorini, L., Maslej, N., Besiroglu, T., Owen, D.: The rising costs of training frontier AI models. arXiv preprint arXiv:2405.21015 (2024)"},{"key":"19_CR6","unstructured":"Denil, M., Shakibi, B., Dinh, L., Ranzato, M., De\u00a0Freitas, N.: Predicting parameters in deep learning. Adv. Neural Inf. Proc. Syst. 26 (2013)"},{"key":"19_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale (2021)"},{"key":"19_CR8","unstructured":"Evci, U., Gale, T., Menick, J., Castro, P.S., Elsen, E.: Rigging the lottery: making all tickets winners (2021)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Fang, G., Ma, X., Song, M., Mi, M.B., Wang, X.: Depgraph: towards any structural pruning (2023)","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"19_CR10","unstructured":"Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. In: International Conference on Learning Representations (2019)"},{"key":"19_CR11","unstructured":"Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks (2019)"},{"key":"19_CR12","unstructured":"Frantar, E., Alistarh, D.: SparseGPT: Massive language models can be accurately pruned in one-shot. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 10323\u201310337. PMLR (2023)"},{"key":"19_CR13","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep learning. MIT Press (2016)"},{"key":"19_CR14","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding (2016)"},{"key":"19_CR15","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems. vol.\u00a028 (2015)"},{"key":"19_CR16","unstructured":"Hassibi, B., Stork, D.: Second order derivatives for network pruning: optimal brain surgeon. In: Hanson, S., Cowan, J., Giles, C. (eds.) Advances in Neural Information Processing Systems. vol.\u00a05. Morgan-Kaufmann (1992)"},{"key":"19_CR17","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"He, Y., Liu, P., Wang, Z., Hu, Z., Yang, Y.: Filter pruning via geometric median for deep convolutional neural networks acceleration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00447"},{"key":"19_CR19","unstructured":"Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. CoRR abs\/1503.02531 (2015)"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Idelbayev, Y., Carreira-Perpinan, M.A.: Low-rank compression of neural nets: learning the rank of each layer. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8046\u20138056 (2020)","DOI":"10.1109\/CVPR42600.2020.00807"},{"key":"19_CR21","unstructured":"Jiang, A.Q., et al.: Mistral 7b (2023)"},{"key":"19_CR22","unstructured":"Krizhevsky, A., Nair, V., Hinton, G.: Cifar-10 (canadian institute for advanced research)"},{"key":"19_CR23","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems. vol.\u00a025. Curran Associates, Inc. (2012)"},{"issue":"7553","key":"19_CR24","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"19_CR25","unstructured":"LeCun, Y., Denker, J., Solla, S.: Optimal brain damage. In: Touretzky, D. (ed.) Advances in Neural Information Processing Systems. vol.\u00a02. Morgan-Kaufmann (1989)"},{"key":"19_CR26","unstructured":"Lee, J., Park, S., Mo, S., Ahn, S., Shin, J.: Layer-adaptive sparsity for the magnitude-based pruning. In: International Conference on Learning Representations (2021)"},{"key":"19_CR27","unstructured":"Lee, N., Ajanthan, T., Torr, P.H.S.: Snip: single-shot network pruning based on connection sensitivity (2019)"},{"key":"19_CR28","unstructured":"Li, H., Xu, Z., Taylor, G., Studer, C., Goldstein, T.: Visualizing the loss landscape of neural nets. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol.\u00a031. Curran Associates, Inc. (2018)"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., Adamczewski, K., Li, W., Gu, S., Timofte, R., Gool, L.V.: Revisiting random channel pruning for neural network compression (2022)","DOI":"10.1109\/CVPR52688.2022.00029"},{"key":"19_CR30","unstructured":"Liu, S., et al.: Sparse training via boosting pruning plasticity with neuroregeneration. In: Proceedings of the 35th International Conference on Neural Information Processing Systems. NIPS \u201921, Curran Associates Inc., Red Hook, NY, USA (2024)"},{"key":"19_CR31","unstructured":"Liu, S., et al.: The unreasonable effectiveness of random pruning: return of the most naive baseline for sparse training. In: International Conference on Learning Representations (2022)"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2755\u20132763 (2017)","DOI":"10.1109\/ICCV.2017.298"},{"issue":"2","key":"19_CR33","first-page":"313","volume":"19","author":"MP Marcus","year":"1993","unstructured":"Marcus, M.P., Santorini, B., Marcinkiewicz, M.A.: Building a large annotated corpus of english: the penn treebank. Comput. Linguist. 19(2), 313\u2013330 (1993)","journal-title":"Comput. Linguist."},{"key":"19_CR34","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models (2016)"},{"key":"19_CR35","unstructured":"Patterson, D., et al.: Carbon emissions and large neural network training. arXiv preprint arXiv:2104.10350 (2021)"},{"key":"19_CR36","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Guyon, I., et al (eds.) Advances in Neural Information Processing Systems. vol.\u00a030. Curran Associates, Inc. (2017)"},{"key":"19_CR37","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"key":"19_CR38","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI (2019)"},{"key":"19_CR39","doi-asserted-by":"publisher","first-page":"26839","DOI":"10.1109\/ACCESS.2024.3365742","volume":"12","author":"MAK Raiaan","year":"2024","unstructured":"Raiaan, M.A.K., et al.: A review on large language models: architectures, applications, taxonomies, open issues and challenges. IEEE access 12, 26839\u201326874 (2024)","journal-title":"IEEE access"},{"key":"19_CR40","unstructured":"Sabih, M., Hannig, F., Teich, J.: Utilizing explainable AI for quantization and pruning of deep neural networks. CoRR abs\/2008.09072 (2020)"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"19_CR42","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter. ArXiv abs\/1910.01108 (2019)"},{"key":"19_CR43","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 3645\u20133650 (2019)","DOI":"10.18653\/v1\/P19-1355"},{"key":"19_CR45","unstructured":"Sun, M., Liu, Z., Bair, A., Kolter, J.Z.: A simple and effective pruning approach for large language models. In: The Twelfth International Conference on Learning Representations (2024)"},{"issue":"10","key":"19_CR46","first-page":"34","volume":"59","author":"NC Thompson","year":"2022","unstructured":"Thompson, N.C., Greenewald, K., Lee, K., Manso, G.F.: Deep learning\u2019s diminishing returns. IEEE Spectr. 59(10), 34\u201339 (2022)","journal-title":"IEEE Spectr."},{"key":"19_CR47","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models (2023)"},{"key":"19_CR48","unstructured":"Wang, C., Grosse, R.B., Fidler, S., Zhang, G.: Eigendamage: structured pruning in the kronecker-factored eigenbasis. ArXiv abs\/1905.05934 (2019)"},{"key":"19_CR49","unstructured":"Wu, C.J., et\u00a0al.: Sustainable AI: environmental implications, challenges and opportunities. In: Proceedings of Machine Learning and Systems. vol.\u00a04, pp. 795\u2013813 (2022)"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: 3d shapenets: a deep representation for volumetric shapes. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1912\u20131920 (2015)","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"19_CR51","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms (2017)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06106-5_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:14:23Z","timestamp":1782310463000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06106-5_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"ISBN":["9783032061058","9783032061065"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06106-5_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"3 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}