{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T23:36:35Z","timestamp":1783553795434,"version":"3.55.0"},"reference-count":129,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Manipal Academy of Higher Education through IEEE Institutional OA Agreements"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3369417","type":"journal-article","created":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T14:07:35Z","timestamp":1708697255000},"page":"33173-33189","source":"Crossref","is-referenced-by-count":61,"title":["Opportunities and Challenges in Data-Centric AI"],"prefix":"10.1109","volume":"12","author":[{"given":"Sushant","family":"Kumar","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2481-8184","authenticated-orcid":false,"given":"Sumit","family":"Datta","sequence":"additional","affiliation":[{"name":"School of Electronic Systems and Automation, Digital University Kerala (Formerly IIITM Kerala), Thiruvananthapuram, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9683-6504","authenticated-orcid":false,"given":"Vishakha","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9061-6313","authenticated-orcid":false,"given":"Sanjay Kumar","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8542-5096","authenticated-orcid":false,"given":"Ritesh","family":"Sharma","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0307-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jii.2021.100224"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3133846"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CONECCT55679.2022.9865824"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/23998083221105496"},{"key":"ref6","article-title":"Overton: A data system for monitoring and improving machine-learned products","volume-title":"Proc. 10th Conf. Innov. Data Syst. Res.","author":"R\u00e9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2937083"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2022.9754503"},{"key":"ref10","article-title":"Towards efficient datacentric robust machine learning with noise-based augmentation","volume-title":"Proc. AAAI Workshop Adversarial Mach. Learn.","author":"Liu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3194503"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3227225"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITT56123.2022.9863935"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101822"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app13052753"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00516-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-022-00775-9"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3209465"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MTS.2023.3306532"},{"issue":"26","key":"ref20","first-page":"22","article-title":"AI does not have to be too complicated or expensive for your business","volume":"26","author":"Ng","year":"2021","journal-title":"Harvard Bus. Rev."},{"key":"ref21","article-title":"Big data integration for data-centric AI","volume-title":"Proc. 1st Italian Conf. Big Data Data Sci.","author":"Bergamaschi"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2023.3240450"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.stamet.2005.08.005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3542604"},{"key":"ref25","first-page":"1","article-title":"Datacentric AI requires rethinking data notion","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Hajij"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00094"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3240492"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313685"},{"key":"ref29","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Karras"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref31","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_49"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-013-0706-y"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.186"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-85820-3_1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-019-00552-1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3314036"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14778\/3291264.3291268"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401965"},{"issue":"13","key":"ref41","first-page":"2182","article-title":"SeeDB: Efficient data-driven visualization recommendations to support visual analytics","volume-title":"Proc. VLDB Endowment Int. Conf. Very Large Data Bases","volume":"8","author":"Vartak"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064019"},{"issue":"1","key":"ref43","first-page":"42","article-title":"Validating data and models in continuous ML pipelines","volume":"44","author":"Dreves","year":"2021","journal-title":"IEEE Data Eng. Bull."},{"key":"ref44","first-page":"334","article-title":"Data validation for machine learning","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Breck"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3229867"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00210"},{"key":"ref47","article-title":"Lightweight inspection of data preprocessing in native machine learning pipelines","volume-title":"Proc. Conf. Innov. Data Syst. Res. (CIDR)","author":"Grafberger"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"ref49","article-title":"CleanML: A benchmark for joint data cleaning and machine learning [experiments and analysis]","volume-title":"Proc. 37th IEEE Int. Conf. Data Eng.","author":"Li"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994514"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.14778\/3297753.3297758"},{"key":"ref52","first-page":"7614","article-title":"Transferable clean-label poisoning attacks on deep neural nets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06119-y"},{"key":"ref54","article-title":"Detection of adversarial training examples in poisoning attacks through anomaly detection","author":"Paudice","year":"2018","journal-title":"arXiv:1802.03041"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-01981-2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134057"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-24271-9"},{"key":"ref58","first-page":"960","article-title":"Decoupling \u2018when to update\u2019 from \u2018how to update","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Malach"},{"key":"ref59","first-page":"2304","article-title":"Mentor- Net: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref60","first-page":"8536","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Han"},{"key":"ref61","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052660"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0047"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313559"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2903730"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389726"},{"issue":"2","key":"ref69","first-page":"59","article-title":"Making open data transparent: Data discovery on open data","volume":"41","author":"Miller","year":"2018","journal-title":"IEEE Data Eng. Bull."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref71","author":"Kurach","year":"2019","journal-title":"The GAN Landscape: Losses, Architectures, Regularization, and Normalization"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.14778\/3421424.3421429"},{"key":"ref73","article-title":"ReMixMatch: Semi-supervised learning with distribution matching and augmentation anchoring","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Berthelot"},{"key":"ref74","first-page":"5050","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Berthelot"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref76","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref77","article-title":"Model patching: Closing the subgroup performance gap with data augmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Goel"},{"key":"ref78","volume-title":"Amazon Mechanical Turk","year":"2023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301978"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01560-1"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3506712"},{"issue":"1","key":"ref83","first-page":"24","article-title":"From cleaning before ML to cleaning for ML","volume":"44","author":"Neutatz","year":"2021","journal-title":"IEEE Data Eng. Bull."},{"key":"ref84","first-page":"6914","article-title":"On robust mean estimation under coordinate-level corruption","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref85","author":"Biessmann","year":"2021","journal-title":"Automated Data Validation in Machine Learning Systems"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098021"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054782"},{"key":"ref88","volume-title":"Facets\u2014Know Your Data","year":"2023"},{"key":"ref89","first-page":"61","article-title":"Automating data quality validation for dynamic data ingestion","volume-title":"Proc. EDBT","author":"Redyuk"},{"key":"ref90","first-page":"529","article-title":"JENGA: A framework to study the impact of data errors on the predictions of machine learning models","volume-title":"Proc. EDBT","author":"Schelter"},{"key":"ref91","article-title":"Ease. ML: A lifecycle management system for machine learning","volume-title":"Proc. Annu. Conf. Innov. Data Syst. Res.","author":"Aguilar Melgar"},{"issue":"1","key":"ref92","first-page":"66","article-title":"Enhancing the interactivity of dataframe queries by leveraging think time","volume":"44","author":"Xin","year":"2021","journal-title":"IEEE Data Eng. Bull."},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.14778\/3430915.3430917"},{"issue":"1","key":"ref94","first-page":"11","article-title":"A data quality-driven view of MLOps","volume":"44","author":"Renggli","year":"2021","journal-title":"IEEE Data Eng. Bull."},{"key":"ref95","first-page":"6106","article-title":"Poison frogs! Targeted clean-label poisoning attacks on neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Shafahi"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2008.11"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"issue":"2","key":"ref98","first-page":"3","article-title":"Data integration: The current status and the way forward","volume":"41","author":"Stonebraker","year":"2018","journal-title":"IEEE Data Eng. Bull."},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3533028.3533310"},{"key":"ref100","article-title":"What can data-centric AI learn from data and ML engineering?","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Polyzotis"},{"key":"ref101","article-title":"DataPerf: Benchmarks for data-centric AI development","author":"Mazumder","year":"2022","journal-title":"arXiv:2207.10062"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.semeval-1.87"},{"key":"ref103","first-page":"1","article-title":"A data-centric approach for training deep neural networks with less data","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Motamedi"},{"key":"ref104","first-page":"1789","article-title":"RoboFlow: A data-centric workflow management system for developing AI-enhanced robots","volume-title":"Proc. 5th Conf. Robot Learn.","volume":"164","author":"Lin"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100382"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-18366-7"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2019.06.103"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.3390\/en15030826"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICT4S55073.2022.00015"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2023.103852"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/s44163-023-00050-y"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.106748"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_21"},{"key":"ref114","article-title":"Exploiting the potential of datasets: A data-centric approach for model robustness","volume-title":"Proc. AAAI Workshop Adversarial Mach. Learn.","author":"Zhong"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM55135.2022.10017662"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.3390\/math10193618"},{"key":"ref117","article-title":"Methods for data-centric small satellite anomaly detection and fault prediction","volume-title":"Proc. Small Satell. Conf.","author":"Melville"},{"key":"ref118","first-page":"25792","article-title":"BigBio: A framework for data-centric biomedical natural language processing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Fries"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-022-02616-0"},{"key":"ref120","first-page":"19467","article-title":"Data-suite: Data-centric identification of in-distribution incongruous examples","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Seedat"},{"key":"ref121","article-title":"Augment & valuate: A data enhancement pipeline for data-centric AI","volume-title":"Proc. NeurIPS Data-Centric AI Workshop","author":"Lee"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671795"},{"key":"ref123","article-title":"A data-centric image classification benchmark","volume-title":"Proc. NeurIPS Datacentric AI Workshop","author":"Schmarje"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/3485983.3494856"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.3390\/pr9111895"},{"key":"ref126","article-title":"Edge impulse: An MLOps platform for tiny machine learning","author":"Hymel","year":"2022","journal-title":"arXiv:2212.03332"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2143-3"},{"key":"ref128","volume-title":"Data Science on the Google Cloud Platform","author":"Lakshmanan","year":"2022"},{"key":"ref129","volume-title":"TinyML: Machine Learning With Tensorflow Lite on Arduino and Ultra-Low-Power Microcontrollers","author":"Warden","year":"2019"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10444552.pdf?arnumber=10444552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:47:29Z","timestamp":1777060049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10444552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":129,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3369417","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}