{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T22:26:11Z","timestamp":1769207171627,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"name":"Hyundai Motor Company and Kia."},{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP)","award":["o.RS-2025-02219317"],"award-info":[{"award-number":["o.RS-2025-02219317"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761122","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:18:04Z","timestamp":1762561084000},"page":"1324-1333","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring Diverse Sparse Network Structures via Dynamic Pruning with Weight Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4949-4112","authenticated-orcid":false,"given":"Jinwoo","family":"Kim","sequence":"first","affiliation":[{"name":"Kookmin University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8486-2482","authenticated-orcid":false,"given":"Jongyun","family":"Shin","sequence":"additional","affiliation":[{"name":"Kookmin University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3904-5467","authenticated-orcid":false,"given":"Sangho","family":"An","sequence":"additional","affiliation":[{"name":"Kookmin University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1334-4649","authenticated-orcid":false,"given":"Jangho","family":"Kim","sequence":"additional","affiliation":[{"name":"Kookmin University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Deep Rewiring: Training very sparse deep networks. In Int'l Conf. on Learning Representations.","author":"Bellec Guillaume","year":"2018","unstructured":"Guillaume Bellec, David Kappel, Wolfgang Maass, and Robert Legenstein. 2018. Deep Rewiring: Training very sparse deep networks. In Int'l Conf. on Learning Representations."},{"key":"e_1_3_2_2_2_1","first-page":"129","article-title":"What is the state of neural network pruning","volume":"2","author":"Blalock Davis","year":"2020","unstructured":"Davis Blalock, Jose Javier Gonzalez Ortiz, Jonathan Frankle, and John Guttag. 2020. What is the state of neural network pruning? Proceedings of machine learning and systems, Vol. 2 (2020), 129-146.","journal-title":"Proceedings of machine learning and systems"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00890"},{"key":"e_1_3_2_2_4_1","volume-title":"Solla","author":"Cun Yann L.","year":"1990","unstructured":"Yann L. Cun, John S. Denker, and Sara A. Solla. 1990. Optimal Brain Damage. In Advances in Neural Information Processing Systems 2, David S. Touretzky (Ed.). San Francisco, CA: Morgan Kaufmann, 598-605."},{"key":"e_1_3_2_2_5_1","unstructured":"Pau de Jorge Amartya Sanyal Harkirat Behl Philip Torr Gr\u00e9gory Rogez and Puneet K Dokania. [n.d.]. Progressive Skeletonization: Trimming more fat from a network at initialization. In Int'l Conf. on Learning Representations."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_7_1","volume-title":"Exploiting linear structure within convolutional networks for efficient evaluation. Advances in neural information processing systems","author":"Denton Emily L","year":"2014","unstructured":"Emily L Denton, Wojciech Zaremba, Joan Bruna, Yann LeCun, and Rob Fergus. 2014. Exploiting linear structure within convolutional networks for efficient evaluation. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_2_8_1","volume-title":"Sparse networks from scratch: Faster training without losing performance. arXiv preprint arXiv:1907.04840","author":"Dettmers Tim","year":"2019","unstructured":"Tim Dettmers and Luke Zettlemoyer. 2019. Sparse networks from scratch: Faster training without losing performance. arXiv preprint arXiv:1907.04840 (2019)."},{"key":"e_1_3_2_2_9_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Ding Xiaohan","year":"2019","unstructured":"Xiaohan Ding, Xiangxin Zhou, Yuchen Guo, Jungong Han, Ji Liu, et al., 2019. Global sparse momentum sgd for pruning very deep neural networks. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_10_1","first-page":"2943","article-title":"Rigging the lottery: Making all tickets winners. In Int'l Conf. on machine learning","author":"Evci Utku","year":"2020","unstructured":"Utku Evci, Trevor Gale, Jacob Menick, Pablo Samuel Castro, and Erich Elsen. 2020. Rigging the lottery: Making all tickets winners. In Int'l Conf. on machine learning. PMLR, 2943-2952.","journal-title":"PMLR"},{"key":"e_1_3_2_2_11_1","volume-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635","author":"Frankle Jonathan","year":"2018","unstructured":"Jonathan Frankle and Michael Carbin. 2018. The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635 (2018)."},{"key":"e_1_3_2_2_12_1","first-page":"3259","article-title":"Linear mode connectivity and the lottery ticket hypothesis","author":"Frankle Jonathan","year":"2020","unstructured":"Jonathan Frankle, Gintare Karolina Dziugaite, Daniel Roy, and Michael Carbin. 2020. Linear mode connectivity and the lottery ticket hypothesis. In Int'l Conf. on Machine Learning. PMLR, 3259-3269.","journal-title":"Int'l Conf. on Machine Learning. PMLR"},{"key":"e_1_3_2_2_13_1","volume-title":"Learning both weights and connections for efficient neural network. Advances in neural information processing systems","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William Dally. 2015. Learning both weights and connections for efficient neural network. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_2_14_1","volume-title":"Robust pruning at initialization. arXiv preprint arXiv:2002.08797","author":"Hayou Soufiane","year":"2020","unstructured":"Soufiane Hayou, Jean-Francois Ton, Arnaud Doucet, and Yee Whye Teh. 2020. Robust pruning at initialization. arXiv preprint arXiv:2002.08797 (2020)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_16_1","volume-title":"Flat minima. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Flat minima. Neural computation, Vol. 9, 1 (1997), 1-42."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3692937"},{"key":"e_1_3_2_2_19_1","unstructured":"LIU Junjie XU Zhe SHI Runbin Ray CC Cheung and Hayden KH So. [n.d.]. Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers. In Int'l Conf. on Learning Representations."},{"key":"e_1_3_2_2_20_1","volume-title":"On large-batch training for deep learning: Generalization gap and sharp minima. arXiv preprint arXiv:1609.04836","author":"Keskar Nitish Shirish","year":"2016","unstructured":"Nitish Shirish Keskar, Dheevatsa Mudigere, Jorge Nocedal, Mikhail Smelyanskiy, and Ping Tak Peter Tang. 2016. On large-batch training for deep learning: Generalization gap and sharp minima. arXiv preprint arXiv:1609.04836 (2016)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611741"},{"key":"e_1_3_2_2_22_1","unstructured":"Alex Krizhevsky et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_2_23_1","first-page":"5544","article-title":"Soft threshold weight reparameterization for learnable sparsity","author":"Kusupati Aditya","year":"2020","unstructured":"Aditya Kusupati, Vivek Ramanujan, Raghav Somani, Mitchell Wortsman, Prateek Jain, Sham Kakade, and Ali Farhadi. 2020. Soft threshold weight reparameterization for learnable sparsity. In Int'l Conf. on Machine Learning. PMLR, 5544-5555.","journal-title":"Int'l Conf. on Machine Learning. PMLR"},{"key":"e_1_3_2_2_24_1","volume-title":"Network pruning that matters: A case study on retraining variants. arXiv preprint arXiv:2105.03193","author":"Le Duong H","year":"2021","unstructured":"Duong H Le and Binh-Son Hua. 2021. Network pruning that matters: A case study on retraining variants. arXiv preprint arXiv:2105.03193 (2021)."},{"key":"e_1_3_2_2_25_1","volume-title":"SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY. In Int'l Conf. on Learning Representations.","author":"Lee Namhoon","year":"2018","unstructured":"Namhoon Lee, Thalaiyasingam Ajanthan, and Philip Torr. 2018. SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY. In Int'l Conf. on Learning Representations."},{"key":"e_1_3_2_2_26_1","volume-title":"Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710","author":"Li Hao","year":"2016","unstructured":"Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2016. Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 (2016)."},{"key":"e_1_3_2_2_27_1","unstructured":"Tao Lin Sebastian U. Stich Luis Barba Daniil Dmitriev and Martin Jaggi. 2020. Dynamic Model Pruning with Feedback. In Int'l Conf. on Learning Representations. https:\/\/openreview.net\/forum?id=SJem8lSFwB"},{"key":"e_1_3_2_2_28_1","first-page":"9908","article-title":"Sparse training via boosting pruning plasticity with neuroregeneration","volume":"34","author":"Liu Shiwei","year":"2021","unstructured":"Shiwei Liu, Tianlong Chen, Xiaohan Chen, Zahra Atashgahi, Lu Yin, Huanyu Kou, Li Shen, Mykola Pechenizkiy, Zhangyang Wang, and Decebal Constantin Mocanu. 2021a. Sparse training via boosting pruning plasticity with neuroregeneration. Advances in Neural Information Processing Systems, Vol. 34 (2021), 9908-9922.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_29_1","first-page":"6989","article-title":"Do we actually need dense over-parameterization? in-time over-parameterization in sparse training","author":"Liu Shiwei","year":"2021","unstructured":"Shiwei Liu, Lu Yin, Decebal Constantin Mocanu, and Mykola Pechenizkiy. 2021b. Do we actually need dense over-parameterization? in-time over-parameterization in sparse training. In Int'l Conf. on Machine Learning. PMLR, 6989-7000.","journal-title":"Int'l Conf. on Machine Learning. PMLR"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"e_1_3_2_2_32_1","volume-title":"Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature communications","author":"Mocanu Decebal Constantin","year":"2018","unstructured":"Decebal Constantin Mocanu, Elena Mocanu, Peter Stone, Phuong H Nguyen, Madeleine Gibescu, and Antonio Liotta. 2018. Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature communications, Vol. 9, 1 (2018), 2383."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"e_1_3_2_2_34_1","volume-title":"Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440","author":"Molchanov Pavlo","year":"2016","unstructured":"Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila, and Jan Kautz. 2016. Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440 (2016)."},{"key":"e_1_3_2_2_35_1","first-page":"4646","article-title":"Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization","author":"Mostafa Hesham","year":"2019","unstructured":"Hesham Mostafa and Xin Wang. 2019. Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization. In Int'l Conf. on Machine Learning. PMLR, 4646-4655.","journal-title":"Int'l Conf. on Machine Learning. PMLR"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_35"},{"key":"e_1_3_2_2_37_1","volume-title":"Comparing rewinding and fine-tuning in neural network pruning. arXiv preprint arXiv:2003.02389","author":"Renda Alex","year":"2020","unstructured":"Alex Renda, Jonathan Frankle, and Michael Carbin. 2020. Comparing rewinding and fine-tuning in neural network pruning. arXiv preprint arXiv:2003.02389 (2020)."},{"key":"e_1_3_2_2_38_1","volume-title":"Winning the lottery with continuous sparsification. Advances in neural information processing systems","author":"Savarese Pedro","year":"2020","unstructured":"Pedro Savarese, Hugo Silva, and Michael Maire. 2020. Winning the lottery with continuous sparsification. Advances in neural information processing systems, Vol. 33 (2020), 11380-11390."},{"key":"e_1_3_2_2_39_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_2_40_1","volume-title":"Super-convergence: Very fast training of neural networks using large learning rates. In Artificial intelligence and machine learning for multi-domain operations applications","author":"Smith Leslie N","year":"2019","unstructured":"Leslie N Smith and Nicholay Topin. 2019. Super-convergence: Very fast training of neural networks using large learning rates. In Artificial intelligence and machine learning for multi-domain operations applications, Vol. 11006. SPIE, 369-386."},{"key":"e_1_3_2_2_41_1","first-page":"1189","article-title":"Towards higher ranks via adversarial weight pruning","volume":"36","author":"Tian Yuchuan","year":"2023","unstructured":"Yuchuan Tian, Hanting Chen, Tianyu Guo, Chao Xu, and Yunhe Wang. 2023. Towards higher ranks via adversarial weight pruning. Advances in Neural Information Processing Systems, Vol. 36 (2023), 1189-1207.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_42_1","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention. In Int'l Conf. on machine learning","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In Int'l Conf. on machine learning. PMLR, 10347-10357.","journal-title":"PMLR"},{"key":"e_1_3_2_2_43_1","unstructured":"Chaoqi Wang Guodong Zhang and Roger Grosse. [n.d.]. Picking Winning Tickets Before Training by Preserving Gradient Flow. In Int'l Conf. on Learning Representations."},{"key":"e_1_3_2_2_44_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Wortsman Mitchell","year":"2019","unstructured":"Mitchell Wortsman, Ali Farhadi, and Mohammad Rastegari. 2019. Discovering neural wirings. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_45_1","first-page":"581","article-title":"Pyhessian: Neural networks through the lens of the hessian. In 2020 IEEE Int'l Conf. on big data (Big data)","author":"Yao Zhewei","year":"2020","unstructured":"Zhewei Yao, Amir Gholami, Kurt Keutzer, and Michael W Mahoney. 2020. Pyhessian: Neural networks through the lens of the hessian. In 2020 IEEE Int'l Conf. on big data (Big data). IEEE, 581-590.","journal-title":"IEEE"},{"key":"e_1_3_2_2_46_1","first-page":"20838","article-title":"Mest: Accurate and fast memory-economic sparse training framework on the edge","volume":"34","author":"Yuan Geng","year":"2021","unstructured":"Geng Yuan, Xiaolong Ma, Wei Niu, Zhengang Li, Zhenglun Kong, Ning Liu, Yifan Gong, Zheng Zhan, Chaoyang He, Qing Jin, et al., 2021. Mest: Accurate and fast memory-economic sparse training framework on the edge. Advances in Neural Information Processing Systems, Vol. 34 (2021), 20838-20850.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2016. Wide Residual Networks. In BMVC.","DOI":"10.5244\/C.30.87"},{"key":"e_1_3_2_2_48_1","unstructured":"Aojun Zhou Yukun Ma Junnan Zhu Jianbo Liu Zhijie Zhang Kun Yuan Wenxiu Sun and Hongsheng Li. [n.d.]. Learning N: M Fine-grained Structured Sparse Neural Networks From Scratch. In Int'l Conf. on Learning Representations."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00360"},{"key":"e_1_3_2_2_50_1","unstructured":"Michael H Zhu and Suyog Gupta. 2018. To Prune or Not to Prune: Exploring the Efficacy of Pruning for Model Compression. (2018)."},{"key":"e_1_3_2_2_51_1","unstructured":"Max Zimmer Christoph Spiegel and Sebastian Pokutta. [n.d.]. How I Learned to Stop Worrying and Love Retraining. In The Eleventh Int'l Conf. on Learning Representations."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:39:22Z","timestamp":1765503562000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":51,"alternative-id":["10.1145\/3746252.3761122","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761122","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}