{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:11:11Z","timestamp":1784823071426,"version":"3.55.0"},"reference-count":244,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406306"],"award-info":[{"award-number":["62406306"]}],"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":["92470204"],"award-info":[{"award-number":["92470204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2024YFF0729201"],"award-info":[{"award-number":["2024YFF0729201"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tkde.2025.3622600","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:39:25Z","timestamp":1760636365000},"page":"47-66","source":"Crossref","is-referenced-by-count":54,"title":["A Comprehensive Survey on Data Augmentation"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4403-3308","authenticated-orcid":false,"given":"Zaitian","family":"Wang","sequence":"first","affiliation":[{"name":"Computer Network Information Center, CAS and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1075-0684","authenticated-orcid":false,"given":"Pengfei","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, CAS and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6053-5977","authenticated-orcid":false,"given":"Kunpeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Portland State University, Portland, OR, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3961-5523","authenticated-orcid":false,"given":"Pengyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, The State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-8024","authenticated-orcid":false,"given":"Yanjie","family":"Fu","sequence":"additional","affiliation":[{"name":"Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3675-0199","authenticated-orcid":false,"given":"Chang-Tien","family":"Lu","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2579-7581","authenticated-orcid":false,"given":"Charu C.","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2200-8711","authenticated-orcid":false,"given":"Jian","family":"Pei","sequence":"additional","affiliation":[{"name":"Duke University, Durham, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2144-1131","authenticated-orcid":false,"given":"Yuanchun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, CAS and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i1.32097"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5575-2_11"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref6","article-title":"GPT-4 technical report. arxiv 2303.08774","volume":"2","author":"OpenAI","year":"2023","journal-title":"View Article"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3711118"},{"key":"ref8","first-page":"6810","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/875"},{"key":"ref10","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"key":"ref13","article-title":"GAN augmentation: Augmenting training data using generative adversarial networks","author":"Bowles","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IIPHDW.2018.8388338"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10066-4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2022.100258"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00492-0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3544558"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3575637.3575646"},{"key":"ref23","article-title":"Graph data augmentation for graph machine learning: A survey","author":"Zhao","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3732282"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3229161"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-022-00648-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00792-7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/631"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08459-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0254841"},{"key":"ref31","article-title":"Tabular data augmentation for machine learning: Progress and prospects of embracing generative ai","author":"Cui","year":"2024"},{"key":"ref32","article-title":"A survey on data synthesis and augmentation for large language models","author":"Wang","year":"2024"},{"key":"ref33","article-title":"Image, text, and speech data augmentation using multimodal LLMs for deep learning: A survey","author":"Sapkota","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"ref36","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.381"},{"key":"ref39","article-title":"Gridmask data augmentation","author":"Chen","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIC57457.2023.10049881"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2003.07.002"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57321-8_21"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref44","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref45","article-title":"Augmenting neural machine translation with knowledge graphs","author":"Moussallem","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.234"},{"key":"ref47","article-title":"Data noising as smoothing in neural network language models","author":"Xie","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3301214"},{"key":"ref49","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref50","first-page":"22092","article-title":"Graph random neural networks for semi-supervised learning on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref51","first-page":"19932","article-title":"Large-scale representation learning on graphs via bootstrapping","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Thakoor"},{"key":"ref52","first-page":"14887","article-title":"Graph adversarial self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref53","article-title":"Topological regularization for graph neural networks augmentation","author":"Song","year":"2021"},{"key":"ref54","first-page":"14054","article-title":"Local augmentation for graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25545"},{"key":"ref56","first-page":"11033","article-title":"Vime: Extending the success of self-and semi-supervised learning to tabular domain","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yoon"},{"key":"ref57","first-page":"12918","article-title":"SCARF: Self-supervised contrastive learning using random feature corruption","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bahri"},{"key":"ref58","article-title":"Met: Masked encoding for tabular data","author":"Majmundar","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00307"},{"key":"ref60","article-title":"Collaborative multi-agent reinforcement learning for automated feature transformation with graph-driven path optimization","author":"Huang","year":"2025"},{"key":"ref61","article-title":"Towards data-centric ai: A comprehensive survey of traditional, reinforcement, and generative approaches for tabular data transformation","author":"Wang","year":"2025"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977653.ch87"},{"key":"ref63","first-page":"43563","article-title":"Reinforcement-enhanced autoregressive feature transformation: Gradient-steered search in continuous space for postfix expressions","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/782"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10825204"},{"key":"ref66","first-page":"2570","article-title":"TFWT: Tabular feature weighting with transformer","volume-title":"Proc. 33rd Int. Joint Conf. Artif. Intell.","author":"Zhang"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136817"},{"key":"ref68","article-title":"RobustTAD: Robust time series anomaly detection via decomposition and convolutional neural networks","author":"Gao","year":"2020"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.1998.0193"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053671"},{"issue":"1","key":"ref71","first-page":"3","article-title":"STL: A seasonal-trend decomposition","volume":"6","author":"Cleveland","year":"1990","journal-title":"J. Official Statist."},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015409"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC.2004.1286964"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/1124772.1124886"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/1631272.1631384"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873992"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2223226"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00855"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.130"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2962572"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/1457515.1409071"},{"key":"ref82","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Jaderberg"},{"key":"ref83","article-title":"Patchshuffle regularization","author":"Kang","year":"2017"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1545"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.212"},{"key":"ref86","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref87","first-page":"2502","article-title":"Dropedge: Towards deep graph convolutional networks on node classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rong"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3133818"},{"key":"ref89","first-page":"15920","article-title":"Adversarial graph augmentation to improve graph contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Suresh"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449822"},{"key":"ref92","article-title":"Graphcrop: Subgraph cropping for graph classification","author":"Wang","year":"2020"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00031"},{"key":"ref94","first-page":"11458","article-title":"Robust graph representation learning via neural sparsification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467186"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539347"},{"key":"ref97","first-page":"13366","article-title":"Diffusion improves graph learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gasteiger"},{"key":"ref98","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hassani"},{"key":"ref99","article-title":"Self-supervised graph neural networks without explicit negative sampling","author":"Kefato","year":"2021"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/204"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1009440108"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1093\/comnet\/cnt010"},{"key":"ref103","first-page":"8247","article-title":"Understanding over-squashing and bottlenecks on graphs via curvature","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Topping"},{"key":"ref104","first-page":"15","article-title":"DiffWire: Inductive graph rewiring via the Lov\u00e1sz bound","volume-title":"Proc. Learn. Graphs Conf.","author":"Arnaiz-Rodr\u0131\u01f5uez"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2024.3441766"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583454"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.61"},{"key":"ref108","first-page":"18853","article-title":"Subtab: Subsetting features of tabular data for self-supervised representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ucar"},{"key":"ref109","article-title":"Multi-scale convolutional neural networks for time series classification","author":"Cui","year":"2016"},{"key":"ref110","first-page":"1","article-title":"Data augmentation for time series classification using convolutional neural networks","volume-title":"Proc. ECML\/PKDD Workshop Adv. Analytics Learn. Temporal Data","author":"Le Guennec"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003741"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.3390\/s18092892"},{"key":"ref113","article-title":"Vocal tract length perturbation (VTLP) improves speech recognition","volume-title":"Proc. ICML Workshop Deep Learn. Audio, Speech Lang.","author":"Jaitly"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref115","first-page":"6665","article-title":"Fast autoaugment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lim"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref117","first-page":"2731","article-title":"Population based augmentation: Efficient learning of augmentation policy schedules","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ho"},{"key":"ref118","first-page":"49034","article-title":"Effective data augmentation with diffusion models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Trabucco"},{"key":"ref119","first-page":"22316","article-title":"Advancing fine-grained classification by structure and subject preserving augmentation","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","author":"Michaeli"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2960263"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2025.3536934"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.710"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1084"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref126","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref127","article-title":"Augmix: A simple data processing method to improve robustness and uncertainty","author":"Hendrycks","year":"2019"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00386"},{"key":"ref129","article-title":"Data augmentation by pairing samples for images classification","author":"Inoue","year":"2018"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65414-6_9"},{"key":"ref131","article-title":"Augmenting data with mixup for sentence classification: An empirical study","author":"Guo","year":"2019"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5822"},{"key":"ref133","first-page":"4622","article-title":"Doublemix: Simple interpolation-based data augmentation for text classification","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Chen"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482477"},{"key":"ref135","first-page":"1","article-title":"Learning from labeled and unlabeled data with label propagation","author":"Zhu","year":"2002"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533811"},{"key":"ref137","first-page":"8034","article-title":"Combining label propagation and simple models out-performs graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang"},{"key":"ref138","article-title":"Synthesising multi-modal minority samples for tabular data","author":"Darabi","year":"2021"},{"key":"ref139","article-title":"Contrastive mixup: Self-and semi-supervised learning for tabular domain","author":"Darabi","year":"2021"},{"key":"ref140","article-title":"Saint: Improved neural networks for tabular data via row attention and contrastive pre-training","author":"Somepalli","year":"2021"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref142","article-title":"Excelformer: A neural network surpassing gbdts on tabular data","author":"Chen","year":"2023"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.013"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.106"},{"key":"ref145","article-title":"Dataset augmentation in feature space","author":"DeVries","year":"2017"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2020.101084"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2935128"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053994"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.5220\/0010773700003124"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.676"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.339"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.307"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.385"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.285"},{"key":"ref155","first-page":"2902","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_26"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2696121"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01630"},{"key":"ref159","article-title":"Improving diffusion-based data augmentation with inversion spherical interpolation","author":"Wang","year":"2024"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.192"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.323"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449796"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615280"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25941"},{"key":"ref165","article-title":"Graph mixup with soft alignments","author":"Ling","year":"2023"},{"key":"ref166","first-page":"8230","article-title":"G-mixup: Graph data augmentation for graph classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00036"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107836"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557699"},{"key":"ref170","first-page":"6295","article-title":"Bayesian generative active deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tran"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-6579-2_24"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3116668"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/751"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.013"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4992-2_30"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00854"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21074-8_14"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3051263"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07071-1"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-87660-8_7"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.14778\/3231751.3231757"},{"key":"ref182","first-page":"7335","article-title":"Modeling tabular data using conditional GAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114582"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/287"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad239"},{"key":"ref186","article-title":"Real-valued (medical) time series generation with recurrent conditional GANs","author":"Esteban","year":"2017"},{"key":"ref187","first-page":"5508","article-title":"Time-series generative adversarial networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yoon"},{"key":"ref188","first-page":"4974","article-title":"Adversarial audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Donahue"},{"key":"ref189","article-title":"Molgan: An implicit generative model for small molecular graphs","author":"De Cao","year":"2018"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6233"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.600"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.726"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324923000438"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-36272-9_18"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-85181-0_10"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2024.100614"},{"key":"ref197","first-page":"44060","article-title":"Curated llm: Synergy of llms and data curation for tabular augmentation in low-data regimes","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Seedat"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM59182.2024.00040"},{"key":"ref199","first-page":"27928","article-title":"Time-LLM: Time series forecasting by reprogramming large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jin"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2024.10.184"},{"key":"ref201","first-page":"76558","article-title":"Expanding small-scale datasets with guided imagination","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28084"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_27"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.109"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1061"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1145\/3639283"},{"key":"ref207","article-title":"Tabdiff: A mixed-type diffusion model for tabular data generation","author":"Shi","year":"2024"},{"key":"ref208","first-page":"1288","article-title":"Generating and imputing tabular data via diffusion and flow-based gradient-boosted trees","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Jolicoeur-Martineau"},{"key":"ref209","article-title":"A survey on graph diffusion models: Generative AI in science for molecule, protein and material","author":"Zhang","year":"2023"},{"key":"ref210","first-page":"16506","article-title":"Digress: Discrete denoising diffusion for graph generation","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Vignac"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.23919\/CCC63176.2024.10661965"},{"key":"ref212","article-title":"A time-series data augmentation model through diffusion and transformer integration","author":"Zhang","year":"2025"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_28"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1145\/3588689"},{"key":"ref216","first-page":"32173","article-title":"Hytrel: Hypergraph-enhanced tabular data representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/781"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.470"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.292"},{"key":"ref220","first-page":"32148","article-title":"Goggle: Generative modelling for tabular data by learning relational structure","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref221","first-page":"16373","article-title":"Learning enhanced representation for tabular data via neighborhood propagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Du"},{"key":"ref222","first-page":"1","article-title":"Data preprocessing and augmentation for multiple short time series forecasting with recurrent neural networks","volume-title":"Proc. 36th Int. Symp. Forecasting","author":"Smyl"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1002\/sam.11461"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-2311"},{"key":"ref225","first-page":"13560","article-title":"Tradeoffs in data augmentation: An empirical study","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gontijo-Lopes"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110204"},{"key":"ref227","first-page":"1739","article-title":"Diversity, density, and homogeneity: Quantitative characteristic metrics for text collections","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Lai"},{"key":"ref228","first-page":"4933","article-title":"Can data diversity enhance learning generalization","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Yu"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/ICCT46805.2019.8947189"},{"key":"ref230","article-title":"Co-mixup: Saliency guided joint mixup with supermodular diversity","author":"Kim","year":"2021"},{"key":"ref231","first-page":"5275","article-title":"Puzzle mix: Exploiting saliency and local statistics for optimal mixup","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"ref233","article-title":"Selective text augmentation with word roles for low-resource text classification","author":"Guo","year":"2022"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/496"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1141"},{"key":"ref236","first-page":"71","article-title":"Insertion, deletion, or substitution? normalizing text messages without pre-categorization nor supervision","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Liu"},{"key":"ref237","first-page":"7011","article-title":"Insnet: An efficient, flexible, and performant insertion-based text generation model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449802"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3088844"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412086"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.3390\/min14030275"},{"key":"ref242","article-title":"Dual contrastive learning: Text classification via label-aware data augmentation","author":"Chen","year":"2022"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00107"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91907-7_11"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11288926\/11205970.pdf?arnumber=11205970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T03:56:11Z","timestamp":1765425371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11205970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":244,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3622600","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}