{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T17:04:07Z","timestamp":1763139847105,"version":"3.45.0"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 62206305"],"award-info":[{"award-number":["No. 62206305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 72101265"],"award-info":[{"award-number":["No. 72101265"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s40747-025-02099-x","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T06:16:54Z","timestamp":1761718614000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dataset distillation with stochastic neural networks"],"prefix":"10.1007","volume":"11","author":[{"given":"Zeyuan","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3073-3008","authenticated-orcid":false,"given":"Tianyuan","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Yanming","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Yirun","family":"Ruan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"2099_CR1","unstructured":"Ghorbani B, Firat O, Freitag M, Bapna A, Krikun M, Garcia X, Chelba C, Cherry C (2021) Scaling laws for neural machine translation. arXiv preprint arXiv:2109.07740"},{"key":"2099_CR2","unstructured":"Phillips JM (2016) Coresets and sketches. arXiv preprint arXiv:1601.00617"},{"key":"2099_CR3","doi-asserted-by":"crossref","unstructured":"Guo C, Zhao B, Bai Y (2022) DeepCore: a comprehensive library for coreset selection in deep learning. In: International conference on database and expert systems applications. Springer, pp 181\u2013195","DOI":"10.1007\/978-3-031-12423-5_14"},{"key":"2099_CR4","doi-asserted-by":"crossref","unstructured":"Feldman D (2020) Introduction to core-sets: an updated survey. arXiv preprint arXiv:2011.09384","DOI":"10.1002\/widm.1335"},{"key":"2099_CR5","unstructured":"Mirzasoleiman B, Bilmes J, Leskovec J (2020) Coresets for data-efficient training of machine learning models. In: ICLR. PMLR, pp 6950\u20136960"},{"key":"2099_CR6","doi-asserted-by":"crossref","unstructured":"Wiewel F, Yang B (2021) Condensed composite memory continual learning. In: IJCNN. IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN52387.2021.9533491"},{"key":"2099_CR7","unstructured":"Sachdeva N, McAuley J (2023) Data distillation: a survey. arXiv preprint arXiv:2301.04272"},{"key":"2099_CR8","unstructured":"Duan Y, Zhang J, Zhang L (2023) Dataset distillation in latent space. arXiv preprint arXiv:2311.15547"},{"key":"2099_CR9","unstructured":"Wang T, Zhu J-Y, Torralba A, Efros AA (2018) Dataset distillation. arXiv preprint arXiv:1811.10959"},{"key":"2099_CR10","unstructured":"Zhao B, Mopuri KR, Bilen H (2020) Dataset condensation with gradient matching. arXiv preprint arXiv:2006.05929"},{"key":"2099_CR11","doi-asserted-by":"crossref","unstructured":"Cazenavette G, Wang T, Torralba A, Efros AA, Zhu J-Y (2022) Dataset distillation by matching training trajectories. In: CVPR, pp 4750\u20134759","DOI":"10.1109\/CVPR52688.2022.01045"},{"key":"2099_CR12","doi-asserted-by":"crossref","unstructured":"Zhao B, Bilen H (2023) Dataset condensation with distribution matching. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 6514\u20136523","DOI":"10.1109\/WACV56688.2023.00645"},{"key":"2099_CR13","first-page":"5186","volume":"34","author":"T Nguyen","year":"2021","unstructured":"Nguyen T, Novak R, Xiao L, Lee J (2021) Dataset distillation with infinitely wide convolutional networks. NeurIPS 34:5186\u20135198","journal-title":"NeurIPS"},{"key":"2099_CR14","first-page":"14879","volume":"33","author":"Z Borsos","year":"2020","unstructured":"Borsos Z, Mutny M, Krause A (2020) Coresets via bilevel optimization for continual learning and streaming. NeurIPS 33:14879\u201314890","journal-title":"NeurIPS"},{"key":"2099_CR15","unstructured":"Kim J-H, Kim J, Oh SJ, Yun S, Song H, Jeong J, Ha J-W, Song HO (2022) Dataset condensation via efficient synthetic-data parameterization. In: ICLR. PMLR, pp 11102\u201311118"},{"key":"2099_CR16","doi-asserted-by":"crossref","unstructured":"Geng J, Chen Z, Wang Y, Woisetschlaeger H, Schimmler S, Mayer R, Zhao Z, Rong C (2023) A survey on dataset distillation: approaches, applications and future directions. arXiv preprint arXiv:2305.01975","DOI":"10.24963\/ijcai.2023\/741"},{"key":"2099_CR17","doi-asserted-by":"crossref","unstructured":"Zhang L, Zhang J, Lei B, Mukherjee S, Pan X, Zhao B, Ding C, Li Y, Xu D (2023) Accelerating dataset distillation via model augmentation. In: CVPR, pp 11950\u201311959","DOI":"10.1109\/CVPR52729.2023.01150"},{"issue":"7","key":"2099_CR18","first-page":"2809","volume":"32","author":"Y Liu","year":"2020","unstructured":"Liu Y, Liu S, Wang Y, Lombardi F, Han J (2020) A survey of stochastic computing neural networks for machine learning applications. TNNLS 32(7):2809\u20132824","journal-title":"TNNLS"},{"key":"2099_CR19","unstructured":"Zhao B, Bilen H (2021) Dataset condensation with differentiable Siamese augmentation. In: ICLR. PMLR, pp 12674\u201312685"},{"key":"2099_CR20","unstructured":"Lee S, Chun S, Jung S, Yun S, Yoon S (2022) Dataset condensation with contrastive signals. In: ICLR. PMLR, pp 12352\u201312364"},{"key":"2099_CR21","doi-asserted-by":"crossref","unstructured":"Wang K, Zhao B, Peng X, Zhu Z, Yang S, Wang S, Huang G, Bilen H, Wang X, You Y (2022) CAFE: learning to condense dataset by aligning features. In: CVPR, pp 12196\u201312205","DOI":"10.1109\/CVPR52688.2022.01188"},{"issue":"6","key":"2099_CR22","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1587\/transfun.2023EAL2053","volume":"107","author":"G Li","year":"2023","unstructured":"Li G, Togo R, Ogawa T, Haseyama M (2023) Dataset distillation using parameter pruning. IEICE Trans Fundam Electron Commun Comput Sci 107(6):936\u2013940","journal-title":"IEICE Trans Fundam Electron Commun Comput Sci"},{"key":"2099_CR23","unstructured":"Cui J, Wang R, Si S, Hsieh C-J (2023) Scaling up dataset distillation to ImageNet-1k with constant memory. In: ICML. PMLR, pp 6565\u20136590"},{"key":"2099_CR24","unstructured":"Lee HB, Lee DB, Hwang SJ (2022) Dataset condensation with latent space knowledge factorization and sharing. arXiv preprint arXiv:2208.10494"},{"issue":"1","key":"2099_CR25","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1109\/TPAMI.2023.3322540","volume":"46","author":"S Lei","year":"2023","unstructured":"Lei S, Tao D (2023) A comprehensive survey of dataset distillation. IEEE Trans Pattern Anal Mach Intell 46(1):17\u201332","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2099_CR26","first-page":"14678","volume":"35","author":"D Chen","year":"2022","unstructured":"Chen D, Kerkouche R, Fritz M (2022) Private set generation with discriminative information. NeurIPS 35:14678\u201314690","journal-title":"NeurIPS"},{"key":"2099_CR27","doi-asserted-by":"crossref","unstructured":"Li G, Togo R, Ogawa T, Haseyama M (2020) Soft-label anonymous gastric X-ray image distillation. In: ICIP2020","DOI":"10.1109\/ICIP40778.2020.9191357"},{"key":"2099_CR28","unstructured":"Such FP, Rawal A, Lehman J, Stanley K, Clune J (2020) Generative teaching networks: accelerating neural architecture search by learning to generate synthetic training data. In: ICLR. PMLR, pp 9206\u20139216"},{"key":"2099_CR29","doi-asserted-by":"crossref","unstructured":"Rosasco A, Carta A, Cossu A, Lomonaco V, Bacciu D (2021) Distilled replay: overcoming forgetting through synthetic samples. In: International workshop on continual semi-supervised learning. Springer, pp 104\u2013117","DOI":"10.1007\/978-3-031-17587-9_8"},{"key":"2099_CR30","first-page":"34391","volume":"35","author":"Z Deng","year":"2022","unstructured":"Deng Z, Russakovsky O (2022) Remember the past: distilling datasets into addressable memories for neural networks. NeurIPS 35:34391\u201334404","journal-title":"NeurIPS"},{"key":"2099_CR31","unstructured":"Hu S, Goetz J, Malik K, Zhan H, Liu Z, Liu Y (2022) FedSynth: gradient compression via synthetic data in federated learning. arXiv preprint arXiv:2204.01273"},{"key":"2099_CR32","unstructured":"Neelakantan A, Vilnis L, Le QV, Sutskever I, Kaiser L, Kurach K, Martens J (2015) Adding gradient noise improves learning for very deep networks. arXiv preprint arXiv:1511.06807"},{"key":"2099_CR33","unstructured":"Gal Y, Ghahramani Z (2016) Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: ICLR. PMLR, pp 1050\u20131059"},{"key":"2099_CR34","unstructured":"Dai B, Zhu C, Guo B, Wipf D (2018) Compressing neural networks using the variational information bottleneck. In: ICLR. PMLR, pp 1135\u20131144"},{"key":"2099_CR35","unstructured":"Alemi AA, Fischer I, Dillon JV, Murphy K (2016) Deep variational information bottleneck. arXiv preprint arXiv:1612.00410"},{"key":"2099_CR36","unstructured":"Tishby N, Pereira FC, Bialek W (2000) The information bottleneck method. arXiv preprint arXiv:physics\/0004057"},{"key":"2099_CR37","unstructured":"Graves A (2011) Practical variational inference for neural networks. Neural Inf Proc Syst Neural Inf Proc Syst 24"},{"key":"2099_CR38","unstructured":"Blundell C, Cornebise J, Kavukcuoglu K, Wierstra D (2015) Weight uncertainty in neural networks. In: International conference on machine learning. PMLR, pp 1613\u20131622"},{"issue":"5786","key":"2099_CR39","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504\u2013507","journal-title":"Science"},{"key":"2099_CR40","unstructured":"Rippel O, Gelbart M, Adams R (2014) Learning ordered representations with nested dropout. In: ICLR. PMLR, pp 1746\u20131754"},{"key":"2099_CR41","doi-asserted-by":"crossref","unstructured":"Yu T, Yang Y, Li D, Hospedales T, Xiang T (2021) Simple and effective stochastic neural networks. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 3252\u20133260","DOI":"10.1609\/aaai.v35i4.16436"},{"key":"2099_CR42","unstructured":"Liu Z, Xu Z, Jin J, Shen Z, Darrell T (2023) Dropout reduces underfitting. arXiv preprint arXiv:2303.01500"},{"key":"2099_CR43","unstructured":"Kingma DP, Mohamed S, Rezende DJ, Welling M (2014) Semi-supervised learning with deep generative models. NeurIPS 27"},{"key":"2099_CR44","unstructured":"Krizhevsky A, Hinton G et al (2009) Learning multiple layers of features from tiny images"},{"key":"2099_CR45","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2099_CR46","doi-asserted-by":"crossref","unstructured":"Liu Y, Gu J, Wang K, Zhu Z, Jiang W, You Y (2023) DREAM: efficient dataset distillation by representative matching. arXiv preprint arXiv:2302.14416","DOI":"10.1109\/ICCV51070.2023.01588"},{"key":"2099_CR47","unstructured":"Sagun L, Evci U, Guney VU, Dauphin Y, Bottou L (2017) Empirical analysis of the Hessian of over-parametrized neural networks. arXiv preprint arXiv:1706.04454"},{"key":"2099_CR48","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2099_CR49","unstructured":"Nguyen T, Chen Z, Lee J (2020) Dataset meta-learning from kernel ridge-regression. arXiv preprint arXiv:2011.00050"},{"key":"2099_CR50","first-page":"9813","volume":"35","author":"Y Zhou","year":"2022","unstructured":"Zhou Y, Nezhadarya E, Ba J (2022) Dataset distillation using neural feature regression. NeurIPS 35:9813\u20139827","journal-title":"NeurIPS"},{"key":"2099_CR51","doi-asserted-by":"crossref","unstructured":"Zhao G, Li G, Qin Y, Yu Y (2023) Improved distribution matching for dataset condensation. In: CVPR, pp 7856\u20137865","DOI":"10.1109\/CVPR52729.2023.00759"},{"key":"2099_CR52","doi-asserted-by":"crossref","unstructured":"Zhang H, Li S, Wang P, Zeng D, Ge S (2024) M3D: dataset condensation by minimizing maximum mean discrepancy. In: AAAI, vol 38, pp 9314\u20139322","DOI":"10.1609\/aaai.v38i8.28784"},{"key":"2099_CR53","doi-asserted-by":"crossref","unstructured":"Deng W, Li W, Ding T, Wang L, Zhang H, Huang K, Huo J, Gao Y (2024) Exploiting inter-sample and inter-feature relations in dataset distillation. In: CVPR, pp 17057\u201317066","DOI":"10.1109\/CVPR52733.2024.01614"},{"key":"2099_CR54","doi-asserted-by":"crossref","unstructured":"Li H, Zhou Y, Gu X, Li B, Wang W (2024) Diversified semantic distribution matching for dataset distillation. In: Proceedings of the 32nd ACM international conference on multimedia, pp 7542\u20137550","DOI":"10.1145\/3664647.3680900"},{"key":"2099_CR55","doi-asserted-by":"crossref","unstructured":"Du J, Jiang Y, Tan VY, Zhou JT, Li H (2023) Minimizing the accumulated trajectory error to improve dataset distillation. In: CVPR, pp 3749\u20133758","DOI":"10.1109\/CVPR52729.2023.00365"},{"key":"2099_CR56","doi-asserted-by":"crossref","unstructured":"Liu D, Gu J, Cao H, Trinitis C, Schulz M (2024) Dataset distillation by automatic training trajectories. In: ECCV. Springer, pp 334\u2013351","DOI":"10.1007\/978-3-031-73021-4_20"},{"key":"2099_CR57","doi-asserted-by":"crossref","unstructured":"Sun P, Shi B, Yu D, Lin T (2024) On the diversity and realism of distilled dataset: an efficient dataset distillation paradigm. In: CVPR, pp 9390\u20139399","DOI":"10.1109\/CVPR52733.2024.00897"},{"key":"2099_CR58","doi-asserted-by":"crossref","unstructured":"Shao S, Yin Z, Zhou M, Zhang X, Shen Z (2024) Generalized large-scale data condensation via various backbone and statistical matching. In: CVPR, pp 16709\u201316718","DOI":"10.1109\/CVPR52733.2024.01581"},{"key":"2099_CR59","doi-asserted-by":"crossref","unstructured":"Welling M (2009) Herding dynamical weights to learn. In: ICML, pp 1121\u20131128","DOI":"10.1145\/1553374.1553517"},{"key":"2099_CR60","unstructured":"Toneva M, Sordoni A, Combes RTD, Trischler A, Bengio Y, Gordon GJ (2018) An empirical study of example forgetting during deep neural network learning. arXiv preprint arXiv:1812.05159"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02099-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-02099-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02099-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T17:01:13Z","timestamp":1763139673000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-02099-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":60,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2099"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-02099-x","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"type":"print","value":"2199-4536"},{"type":"electronic","value":"2198-6053"}],"subject":[],"published":{"date-parts":[[2025,10,29]]},"assertion":[{"value":"8 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 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":"Conflict of interest"}}],"article-number":"484"}}