{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:21:53Z","timestamp":1776183713230,"version":"3.50.1"},"reference-count":117,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Birla Institute of Technology and Science (BITS), Pilani Campus, Pilani"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,2,1]]},"DOI":"10.1109\/jiot.2025.3633710","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:42:32Z","timestamp":1763404952000},"page":"3808-3826","source":"Crossref","is-referenced-by-count":1,"title":["A Comprehensive Survey on Data Distillation: Techniques, Frameworks, and Future Directions"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5352-6870","authenticated-orcid":false,"given":"Qaiser","family":"Razi","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Birla Institute of Technology and Science, Pilani Campus, Pilani, Rajasthan, India"}]},{"given":"Somya","family":"Singh","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Kalinga Institute of Industrial Technology (KIIT), Bhubaneswar, Odisha, India"}]},{"given":"Riya","family":"Priyadarshini","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Kalinga Institute of Industrial Technology (KIIT), Bhubaneswar, Odisha, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9023-1661","authenticated-orcid":false,"given":"Vikas","family":"Hassija","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Kalinga Institute of Industrial Technology (KIIT), Bhubaneswar, Odisha, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4087-7208","authenticated-orcid":false,"given":"G. S. S.","family":"Chalapathi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Birla Institute of Technology and Science, Pilani Campus, Pilani, Rajasthan, India"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"The digitization of the world from edge to core","volume":"16","author":"Rydning","year":"2018","journal-title":"Framingham, Int. Data Corp."},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref4","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.199"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3323376"},{"key":"ref8","article-title":"Understanding multi-task scaling in machine translation","author":"Fernandes","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref11","article-title":"Remember the past: Distilling datasets into addressable memories for neural networks","author":"Deng","year":"2022","journal-title":"arXiv:2206.02916"},{"key":"ref12","article-title":"On-device learning: A survey and outlook","author":"Li","year":"2020","journal-title":"ACM Comput. Surv."},{"key":"ref13","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u00fd","year":"2016","journal-title":"arXiv:1610.05492"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-017-9611-1"},{"key":"ref15","article-title":"Dataset distillation","author":"Wang","year":"2018","journal-title":"arXiv:1811.10959"},{"key":"ref16","article-title":"Self-supervised dataset distillation for transfer learning","author":"Lee","year":"2023","journal-title":"arXiv:2310.06511"},{"key":"ref17","article-title":"DiM: Distilling dataset into generative model","author":"Wang","year":"2023","journal-title":"arXiv:2303.04707"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/741"},{"key":"ref19","article-title":"Data distillation: A survey","author":"Sachdeva","year":"2023","journal-title":"arXiv:2301.04272"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322540"},{"key":"ref21","article-title":"Dataset meta-learning from kernel ridge-regression","author":"Nguyen","year":"2020","journal-title":"arXiv:2011.00050"},{"key":"ref22","article-title":"Graph condensation for graph neural networks","author":"Jin","year":"2021","journal-title":"arXiv:2110.07580"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00645"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref25","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icat.2015.7340515"},{"key":"ref28","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016","journal-title":"arXiv:1612.03928"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"ref31","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00433"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553517"},{"key":"ref34","article-title":"Super-samples from kernel herding","author":"Chen","year":"2012","journal-title":"arXiv:1203.3472"},{"key":"ref35","first-page":"1","article-title":"Scalable training of mixture models via coresets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Feldman"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref38","first-page":"1","article-title":"Practical Bayesian optimization of machine learning algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Snoek"},{"key":"ref39","first-page":"115","article-title":"Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","volume":"28","author":"Bergstra"},{"key":"ref40","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv:1411.1784"},{"key":"ref41","first-page":"9206","article-title":"Generative teaching networks: Accelerating neural architecture search by learning to generate synthetic training data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Such"},{"key":"ref42","first-page":"12674","article-title":"Dataset condensation with differentiable Siamese augmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao"},{"key":"ref43","article-title":"Understanding short-horizon bias in stochastic meta-optimization","author":"Wu","year":"2018","journal-title":"arXiv:1803.02021"},{"key":"ref44","first-page":"4556","article-title":"Understanding and correcting pathologies in the training of learned optimizers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Metz"},{"key":"ref45","first-page":"9813","article-title":"Dataset distillation using neural feature regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref46","first-page":"13877","article-title":"Efficient dataset distillation using random feature approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Loo"},{"key":"ref47","first-page":"13363","article-title":"A generalized neural tangent kernel analysis for two-layer neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref48","article-title":"Wide neural networks of any depth evolve as linear models under gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lee"},{"key":"ref49","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wang"},{"key":"ref50","first-page":"15156","article-title":"Finite versus infinite neural networks: An empirical study","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lee"},{"key":"ref51","volume":"118","author":"Neal","year":"2012","journal-title":"Bayesian Learning for Neural Networks"},{"key":"ref52","article-title":"Deep neural networks as Gaussian processes","author":"Lee","year":"2017","journal-title":"arXiv:1711.00165"},{"key":"ref53","article-title":"Privacy for free: How does dataset condensation help privacy?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dong"},{"key":"ref54","first-page":"11102","article-title":"Dataset condensation via efficient synthetic-data parameterization","volume-title":"Proc. 39th Int. Conf. Mach. Learn. (ICML)","author":"Kim"},{"key":"ref55","first-page":"12352","article-title":"Dataset condensation with contrastive signals","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533769"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01188"},{"key":"ref58","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2016","journal-title":"arXiv:1602.05629"},{"key":"ref59","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017","journal-title":"arXiv:1703.03400"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00521"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313488"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401281"},{"key":"ref63","first-page":"6565","article-title":"Scaling up dataset distillation to ImageNet-1K with constant memory","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cui"},{"key":"ref64","article-title":"Dataset condensation with gradient matching","author":"Zhao","year":"2020","journal-title":"arXiv:2006.05929"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref66","article-title":"LaMDA: Language models for dialog applications","author":"Thoppilan","year":"2022","journal-title":"arXiv:2201.08239"},{"key":"ref67","article-title":"Advances in tabular data processing for machine learning","author":"Shang","year":"2021","journal-title":"J. AI Res."},{"key":"ref68","article-title":"Generating synthetic data for tabular learning","volume-title":"Proc. NeurIPS","author":"Yoon"},{"key":"ref69","article-title":"Handling missing values in tabular data distillation","author":"Xu","year":"2019","journal-title":"IEEE Trans. Data Sci."},{"key":"ref70","article-title":"Gradient-based optimization for efficient dataset distillation","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17587-9_8"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892299"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533491"},{"key":"ref76","first-page":"34391","article-title":"Remember the past: Distilling datasets into addressable memories for neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Deng"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref78","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"Kone\u010dn\u00fd","year":"2016","journal-title":"arXiv:1610.02527"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3048439"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3390\/s21206886"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003925"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0316-z"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1136\/svn-2017-000101"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2016.2636665"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i18.17945"},{"key":"ref88","first-page":"14678","article-title":"Private set generation with discriminative information","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref89","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017","journal-title":"arXiv:1706.06083"},{"key":"ref90","article-title":"Towards robust dataset learning","author":"Wu","year":"2022","journal-title":"arXiv:2211.10752"},{"key":"ref91","article-title":"Speeding up NAS with adaptive subset selection","author":"White","year":"2022","journal-title":"arXiv:2211.01454"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3508804"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00169"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00029"},{"issue":"5","key":"ref95","first-page":"2103","article-title":"A comprehensive review on dataset distillation techniques for efficient ai model training","volume":"32","author":"Ren","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref96","article-title":"Generalized kernel inducing points by duality gap for dataset distillation","author":"Aoyama","year":"2025","journal-title":"arXiv:2502.12607"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01568"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3387328"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2024.3524025"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107189"},{"key":"ref101","first-page":"810","article-title":"DC-BENCH: Dataset condensation benchmark","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Cui"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/DOCS67533.2025.11200827"},{"key":"ref103","article-title":"Information compensation: A fix for any-scale dataset distillation","volume-title":"Proc. ICLR","author":"Sun"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00765"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2023.24287"},{"key":"ref106","article-title":"Universal feature matching for cross-architecture dataset distillation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref107","article-title":"Towards architecture-agnostic dataset distillation","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref108","first-page":"1","article-title":"Enhancing cross-architecture generalization in dataset distillation","volume":"25","author":"Liu","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref109","first-page":"31292","article-title":"Infinite recommendation networks: A data-centric approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sachdeva"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00897"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.01.063"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-78757-w"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11363065\/11250975.pdf?arnumber=11250975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:03:43Z","timestamp":1769493823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11250975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,1]]},"references-count":117,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3633710","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,1]]}}}