{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:09:03Z","timestamp":1792789743048,"version":"4.5.0"},"reference-count":188,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T00:00:00Z","timestamp":1672704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T00:00:00Z","timestamp":1672704000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2018R1A5A1059921"],"award-info":[{"award-number":["NRF-2018R1A5A1059921"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation","award":["2020-0-00862"],"award-info":[{"award-number":["2020-0-00862"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["NRF-2022R1A2C2004382"],"award-info":[{"award-number":["NRF-2022R1A2C2004382"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation","award":["2022-0-00157"],"award-info":[{"award-number":["2022-0-00157"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s00778-022-00775-9","type":"journal-article","created":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T02:03:45Z","timestamp":1672711425000},"page":"791-813","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":543,"title":["Data collection and quality challenges in deep learning: a data-centric AI perspective"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6419-931X","authenticated-orcid":false,"given":"Steven Euijong","family":"Whang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8110-5397","authenticated-orcid":false,"given":"Yuji","family":"Roh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1105-0818","authenticated-orcid":false,"given":"Hwanjun","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8711-7732","authenticated-orcid":false,"given":"Jae-Gil","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,1,3]]},"reference":[{"key":"775_CR1","unstructured":"Amazon Mechanical Turk. https:\/\/www.mturk.com\/. Accessed 13 July 2022"},{"key":"775_CR2","unstructured":"Amazon SageMaker Ground Truth. https:\/\/aws.amazon.com\/sagemaker\/groundtruth\/. Accessed 13 July 2022"},{"key":"775_CR3","unstructured":"Amazon scraps secret AI recruiting tool that showed bias against women. https:\/\/www.reuters.com\/article\/us-amazon-com-jobs-automation-insight-idUSKCN1MK08G. Accessed 13 July 2022"},{"key":"775_CR4","unstructured":"Agarwal, A., Beygelzimer, A., Dud\u00edk, M., Langford, J., Wallach., H.M.: A reductions approach to fair classification. In: ICML, pp. 60\u201369 (2018)"},{"key":"775_CR5","doi-asserted-by":"crossref","unstructured":"Agrawal, P., Arya, R., Bindal, A., Bhatia, S., Gagneja, Godlewski, J., Low, Y., Muss, T., Paliwal, M.M., Raman, S., Shah, V., Shen, Sugden, L., Zhao, K., Wu, M.-C.: Data platform for machine learning. In: SIGMOD, pp. 1803\u20131816 (2019)","DOI":"10.1145\/3299869.3314050"},{"key":"775_CR6","doi-asserted-by":"crossref","unstructured":"Amershi, S., Begel, A., Bird, C., DeLine, R., Gall, H.C., Kamar, E., Nagappan, N., Nushi, B., Zimmermann, T.: Software engineering for machine learning: a case study. In: ICSE, pp. 291\u2013300 (2019)","DOI":"10.1109\/ICSE-SEIP.2019.00042"},{"key":"775_CR7","unstructured":"Angwin, J., Larson, J., Mattu, S., Kirchner, L.: Machine bias: there\u2019s software used across the country to predict future criminals. And its biased against blacks (2016)"},{"key":"775_CR8","doi-asserted-by":"crossref","unstructured":"Anwar, S., Barnes, N.: Real image denoising with feature attention. In: CVPR, pp. 3155\u20133164 (2019)","DOI":"10.1109\/ICCV.2019.00325"},{"key":"775_CR9","doi-asserted-by":"crossref","unstructured":"Asudeh, A., Jin, Z., Jagadish, H.V.: Assessing and remedying coverage for a given dataset. In: ICDE, pp. 554\u2013565 (2019)","DOI":"10.1109\/ICDE.2019.00056"},{"key":"775_CR10","doi-asserted-by":"crossref","unstructured":"Bach, S.H., Rodriguez, D., Liu, Y., Luo, C., Shao, H., Xia, C., Sen, S., Ratner, A., Hancock, B., Alborzi, H., Kuchhal, R., R\u00e9, C.,Malkin, R.: Snorkel Drybell: a case study in deploying weak supervision at industrial scale. In: SIGMOD, pp. 362\u2013375 (2019)","DOI":"10.1145\/3299869.3314036"},{"issue":"2","key":"775_CR11","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltrusaitis","year":"2019","unstructured":"Baltrusaitis, T., Ahuja, C., Morency, L.-P.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 423\u2013443 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"775_CR12","unstructured":"Barocas, S., Hardt, M., Narayanan, A.: Fairness and machine learning. fairmlbook.org. http:\/\/www.fairmlbook.org (2019)"},{"key":"775_CR13","unstructured":"Baylor, D., Breck, E., Cheng, H.-T., Fiedel, N., Foo, C.Y., Haque, Z., Haykal, S., Ispir, M., Jain, V., Koc, L., Koo, C.Y., Lew, L., Mewald, C., Modi, A.N., Polyzotis, N., Ramesh, S., Roy, S., Whang, S.E., Wicke, M., Wilkiewicz, J., Zhang, X., Zinkevich, M.: TFX: a tensorflow-based production-scale machine learning platform. In: KDD, pp. 1387\u20131395 (2017)"},{"key":"775_CR14","doi-asserted-by":"publisher","first-page":"4:1","DOI":"10.1147\/JRD.2019.2942287","volume":"63","author":"RKE Bellamy","year":"2019","unstructured":"Bellamy, R.K.E., Dey, K., Hind, M., et al.: AI fairness 360: an extensible toolkit for detecting and mitigating algorithmic bias. IBM J. Res. Dev. 63, 4:1-4:15 (2019)","journal-title":"IBM J. Res. Dev."},{"key":"775_CR15","doi-asserted-by":"crossref","unstructured":"Berk, R., Heidari, H., Jabbari, S., Kearns, M., Roth, A.: Fairness in criminal justice risk assessments: the state of the art (2017)","DOI":"10.1177\/0049124118782533"},{"key":"775_CR16","unstructured":"Berthelot, D., Carlini, N., Cubuk, E.D., Kurakin, A., Sohn, K., Zhang, H., Raffel, C.: Remixmatch: semi-supervised learning with distribution matching and augmentation anchoring. In: ICLR (2020)"},{"key":"775_CR17","unstructured":"Berthelot, D., Carlini, N., Goodfellow, I.J., Papernot, N., Oliver, A., Raffel, C.: Mixmatch: a holistic approach to semi-supervised learning. In: NeurIPS, pp. 5050\u20135060 (2019)"},{"issue":"1","key":"775_CR18","first-page":"51","volume":"44","author":"F Biessmann","year":"2021","unstructured":"Biessmann, F., Golebiowski, J., Rukat, T., Lange, D., Schmidt, P.: Automated data validation in machine learning systems. IEEE Data Eng. Bull. 44(1), 51\u201365 (2021)","journal-title":"IEEE Data Eng. Bull."},{"key":"775_CR19","doi-asserted-by":"crossref","unstructured":"Biggio, B., Corona, I., Maiorca, D., Nelson, B., Srndic, N., Laskov, P., Giacinto, G., Roli, F.: Evasion attacks against machine learning at test time. In: ECML PKDD, pp. 387\u2013402. Springer (2013)","DOI":"10.1007\/978-3-642-40994-3_25"},{"key":"775_CR20","doi-asserted-by":"crossref","unstructured":"Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT, pp. 92\u2013100. ACM, New York (1998)","DOI":"10.1145\/279943.279962"},{"key":"775_CR21","unstructured":"Boehm, M., Antonov, I., Baunsgaard, S., Dokter, M., Ginth\u00f6r, R., Innerebner, K., Klezin, F., Lindstaedt, S.N., Phani, A., Rath, B., Reinwald, B., Siddiqui, S., Wrede, S.B.: Systemds: a declarative machine learning system for the end-to-end data science lifecycle. In: CIDR (2020)"},{"key":"775_CR22","unstructured":"Breck, E., Zinkevich, M., Polyzotis, N., Whang, S., Roy, S.: Data validation for machine learning. In: MLSys (2019)"},{"key":"775_CR23","doi-asserted-by":"crossref","unstructured":"Brickley, D., Burgess, M., Noy, N.F.: Google dataset search: building a search engine for datasets in an open web ecosystem. In: WWW, pp. 1365\u20131375 (2019)","DOI":"10.1145\/3308558.3313685"},{"key":"775_CR24","unstructured":"CrowdFlower Data Science Report. https:\/\/visit.figure-eight.com\/rs\/416-ZBE-142\/images\/CrowdFlower_DataScienceReport_2016.pdf"},{"issue":"12","key":"775_CR25","first-page":"2140","volume":"11","author":"MJ Cafarella","year":"2018","unstructured":"Cafarella, M.J., Halevy, A.Y., Lee, H., Madhavan, J., Cong, Y., Wang, D.Z., Wu, E.: Ten years of webtables. PVLDB 11(12), 2140\u20132149 (2018)","journal-title":"PVLDB"},{"issue":"11","key":"775_CR26","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.14778\/3137628.3137641","volume":"10","author":"J Cambronero","year":"2017","unstructured":"Cambronero, J., Feser, J.K., Smith, M.J., Madden, S.: Query optimization for dynamic imputation. Proc. VLDB Endow. 10(11), 1310\u20131321 (2017)","journal-title":"Proc. VLDB Endow."},{"key":"775_CR27","unstructured":"Chakraborty, A., Alam, M., Dey, V., Chattopadhyay, A., Mukhopadhyay, D.: Adversarial attacks and defences: a survey. CoRR arXiv:1810.00069 (2018)"},{"key":"775_CR28","unstructured":"Chang, H.-S., Learned-Miller, E.G., McCallum., A.: Active bias: training more accurate neural networks by emphasizing high variance samples. In: NeurIPS, pp. 1002\u20131012 (2017)"},{"issue":"1","key":"775_CR29","first-page":"6085","volume":"8","author":"Z Che","year":"2018","unstructured":"Che, Z., Purushotham, S., Cho, K., Sontag, D., Liu, Y.: Recurrent neural networks for multivariate time series with missing values. Nat. Sci. Rep. 8(1), 6085 (2018)","journal-title":"Nat. Sci. Rep."},{"key":"775_CR30","doi-asserted-by":"crossref","unstructured":"Chen, A., Chow, A., Davidson, A., DCunha, A., Ghodsi, A., Hong, S.A., Konwinski, A., Mewald, C., Murching, S., Nykodym, T., Ogilvie, P., Parkhe, M., Singh, A., Xie, F., Zaharia, M., Zang, R., Zheng, J., Zumar, C.: Developments in mlflow: a system to accelerate the machine learning lifecycle. In: DEEM@SIGMOD, pp. 5:1\u20135:4 (2020)","DOI":"10.1145\/3399579.3399867"},{"key":"775_CR31","unstructured":"Chen, I.Y., Johansson, F.D., Sontag, D.A.: Why is my classifier discriminatory? In: NeurIPS, pp. 3543\u20133554 (2018)"},{"key":"775_CR32","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: KDD, pp. 785\u2013794 (2016)","DOI":"10.1145\/2939672.2939785"},{"key":"775_CR33","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Diakonikolas, I., Ge, R.: High-dimensional robust mean estimation in nearly-linear time. In: SIAM, pp. 2755\u20132771 (2019)","DOI":"10.1137\/1.9781611975482.171"},{"key":"775_CR34","unstructured":"Choi, K., Grover, A., Singh, T., Shu, R., Ermon, S.: Fair generative modeling via weak supervision. In: ICML, pp. 1887\u20131898 (2020)"},{"issue":"2","key":"775_CR35","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1089\/big.2016.0047","volume":"5","author":"A Chouldechova","year":"2017","unstructured":"Chouldechova, A.: Fair prediction with disparate impact: a study of bias in recidivism prediction instruments. Big Data 5(2), 153\u2013163 (2017)","journal-title":"Big Data"},{"issue":"5","key":"775_CR36","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1145\/3376898","volume":"63","author":"A Chouldechova","year":"2020","unstructured":"Chouldechova, A., Roth, A.: A snapshot of the frontiers of fairness in machine learning. Commun. ACM 63(5), 82\u201389 (2020)","journal-title":"Commun. ACM"},{"key":"775_CR37","unstructured":"Chzhen, E., Denis, C., Hebiri, M., Oneto, L., Pontil, M.: Leveraging labeled and unlabeled data for consistent fair binary classification. In: NeurIPS, pp. 12739\u201312750 (2019)"},{"key":"775_CR38","unstructured":"Cotter, A., Jiang, H., Sridharan, K.: Two-player games for efficient non-convex constrained optimization. In: ALT, pp. 300\u2013332 (2019)"},{"key":"775_CR39","doi-asserted-by":"crossref","unstructured":"Cretu, G.F., Stavrou, A., Locasto, M.E., Stolfo, S.J., Keromytis, A.D.: Casting out demons: sanitizing training data for anomaly sensors. In: IEEE S &P, pp. 81\u201395 (2008)","DOI":"10.1109\/SP.2008.11"},{"key":"775_CR40","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Man\u00e9, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: CVPR, pp. 113\u2013123 (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"775_CR41","unstructured":"Data age 2025. https:\/\/www.seagate.com\/our-story\/data-age-2025\/"},{"key":"775_CR42","unstructured":"Data-centric AI resource hub. https:\/\/datacentricai.org\/"},{"key":"775_CR43","unstructured":"Data prep still dominates data scientists\u2019 time, survey finds. https:\/\/www.datanami.com\/2020\/07\/06\/data-prep-still-dominates-data-scientists-time-survey-finds\/"},{"issue":"2","key":"775_CR44","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1137\/17M1126680","volume":"48","author":"I Diakonikolas","year":"2019","unstructured":"Diakonikolas, I., Kamath, G., Kane, D., Li, J., Moitra, A., Stewart, A.: Robust estimators in high-dimensions without the computational intractability. SIAM J. Comput. 48(2), 742\u2013864 (2019)","journal-title":"SIAM J. Comput."},{"key":"775_CR45","unstructured":"Dieterich, W., Mendoza, C., Brennan, T.: Compas risk scales: demonstrating accuracy equity and predictive parity. Technical report, Northpoint Inc (2016)"},{"key":"775_CR46","volume-title":"Principles of Data Integration","author":"A Doan","year":"2012","unstructured":"Doan, A., Halevy, A.Y., Ives, Z.G.: Principles of Data Integration. Morgan Kaufmann, Burlington (2012)"},{"issue":"4","key":"775_CR47","first-page":"376","volume":"12","author":"M Dolatshah","year":"2018","unstructured":"Dolatshah, M., Teoh, M., Wang, J., Pei, J.: Cleaning crowdsourced labels using oracles for statistical classification. PVLDB 12(4), 376\u2013389 (2018)","journal-title":"PVLDB"},{"key":"775_CR48","doi-asserted-by":"crossref","unstructured":"Dong, X.L., Rekatsinas, T.: Data integration and machine learning: a natural synergy. In: KDD, pp. 3193\u20133194 (2019)","DOI":"10.1145\/3292500.3332296"},{"issue":"1","key":"775_CR49","first-page":"42","volume":"44","author":"M Dreves","year":"2021","unstructured":"Dreves, M., Huang, G., Peng, Z., Polyzotis, N., Rosen, E., Paul Suganthan, G.C.: Validating data and models in continuous ML pipelines. IEEE Data Eng. Bull. 44(1), 42\u201350 (2021)","journal-title":"IEEE Data Eng. Bull."},{"key":"775_CR50","unstructured":"Dua, D., Graff, C.: UCI machine learning repository (2017)"},{"key":"775_CR51","doi-asserted-by":"crossref","unstructured":"Dwork, C., Hardt, M., Pitassi, T., Reingold, O., Zemel, R.S.: Fairness through awareness. In: ITCS, pp. 214\u2013226 (2012)","DOI":"10.1145\/2090236.2090255"},{"key":"775_CR52","unstructured":"Facets\u2014visualization for ML datasets. https:\/\/pair-code.github.io\/facets\/. Accessed 13 July 2022"},{"key":"775_CR53","doi-asserted-by":"crossref","unstructured":"Feldman, M., Friedler, S.A., Moeller, J., Scheidegger, C., Venkatasubramanian, S.: Certifying and removing disparate impact. In: KDD, pp. 259\u2013268 (2015)","DOI":"10.1145\/2783258.2783311"},{"key":"775_CR54","unstructured":"Fernandez, R.C., Abedjan, Z., Koko, F., Yuan, G., Madden, S., Stonebraker, M.: Aurum: a data discovery system. In: ICDE, pp. 1001\u20131012 (2018)"},{"issue":"2","key":"775_CR55","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1111\/j.1467-9868.2007.00643.x","volume":"70","author":"DP Foster","year":"2008","unstructured":"Foster, D.P., Stine, R.A.: Alpha-investing: a procedure for sequential control of expected false discoveries. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 70(2), 429\u2013444 (2008)","journal-title":"J. R. Stat. Soc. Ser. B (Stat. Methodol.)"},{"key":"775_CR56","unstructured":"GCP AI platform data labeling service. https:\/\/cloud.google.com\/ai-platform\/data-labeling\/docs. Accessed 13 July 2022"},{"key":"775_CR57","unstructured":"Google apologises for Photos app\u2019s racist blunder. https:\/\/www.bbc.com\/news\/technology-33347866. Accessed 13 July 2022"},{"key":"775_CR58","unstructured":"Goel, K., Albert, G., Li, Y., R\u00e9, C.: Model patching: closing the subgroup performance gap with data augmentation. In: ICLR (2021)"},{"key":"775_CR59","unstructured":"Goodfellow, I.J.: NIPS 2016 tutorial: generative adversarial networks. CoRR arXiv:1701.00160 (2017)"},{"key":"775_CR60","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A.C., Bengio, Y.: Generative adversarial nets. In: NIPS, pp. 2672\u20132680 (2014)"},{"key":"775_CR61","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: ICLR (2015)"},{"key":"775_CR62","unstructured":"Gordon, J.: Introducing tensorflow hub: a library for reusable machine learning modules in tensorflow (2018)"},{"key":"775_CR63","unstructured":"Grafberger, S., Stoyanovich, J., Schelter, S.: Lightweight inspection of data preprocessing in native machine learning pipelines. In: CIDR (2021)"},{"key":"775_CR64","doi-asserted-by":"crossref","unstructured":"Halevy, A.Y., Korn, F., Noy, N.F., Olston, C., Polyzotis, N., Roy, S., Whang, S.E.: Goods: organizing Google\u2019s datasets. In: SIGMOD, pp. 795\u2013806 (2016)","DOI":"10.1145\/2882903.2903730"},{"key":"775_CR65","unstructured":"Han, B., Yao, Q., Yu, X., Niu, G., Xu, M., Hu, W., Tsang, I.W., M. Sugiyama. Co-teaching: robust training of deep neural networks with extremely noisy labels. In: NeurIPS, pp. 8536\u20138546 (2018)"},{"key":"775_CR66","unstructured":"Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. In: NIPS, pp. 3315\u20133323 (2016)"},{"key":"775_CR67","unstructured":"Hashimoto, T.B., Srivastava, M., Namkoong, H., Liang, P.: Fairness without demographics in repeated loss minimization. In: Dy, J.G., Krause, A. (eds.) ICML, vol.\u00a080, pp. 1934\u20131943. PMLR (2018)"},{"key":"775_CR68","doi-asserted-by":"crossref","unstructured":"Hazelwood, K.M., Bird, S., Brooks, D.M., Chintala, S., Diril, U., Dzhulgakov, D., Fawzy, M., Jia, B., Jia, Y., Kalro, A., Law, J., Lee, K., Lu, J., Noordhuis, P., Smelyanskiy, M., Xiong, L., Wang, X.: Applied machine learning at Facebook: a datacenter infrastructure perspective. In: HPCA, pp. 620\u2013629 (2018)","DOI":"10.1109\/HPCA.2018.00059"},{"key":"775_CR69","unstructured":"Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: Augmix: a simple data processing method to improve robustness and uncertainty. In: ICLR (2020)"},{"key":"775_CR70","doi-asserted-by":"crossref","unstructured":"Heo, G., Roh, Y., Hwang, S., Lee, D., Whang, S.E.: Inspector gadget: a data programming-based labeling system for industrial images. In: PVLDB (2021)","DOI":"10.14778\/3421424.3421429"},{"key":"775_CR71","unstructured":"Hermann, J.M., Baso, D.: Meet michelangelo: Uber\u2019s machine learning platform (2017)"},{"issue":"2","key":"775_CR72","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1023\/B:AIRE.0000045502.10941.a9","volume":"22","author":"VJ Hodge","year":"2004","unstructured":"Hodge, V.J., Austin, J.: A survey of outlier detection methodologies. Artif. Intell. Rev. 22(2), 85\u2013126 (2004)","journal-title":"Artif. Intell. Rev."},{"key":"775_CR73","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1007\/978-1-4612-4380-9_35","volume-title":"Breakthroughs in Statistics","author":"PJ Huber","year":"1992","unstructured":"Huber, P.J.: Robust estimation of a location parameter. In: Kotz, S., Johnson, N.L. (eds.) Breakthroughs in Statistics, pp. 492\u2013518. Springer, Berlin (1992)"},{"key":"775_CR74","doi-asserted-by":"publisher","DOI":"10.1145\/3310205","volume-title":"Data Cleaning","author":"IF Ilyas","year":"2019","unstructured":"Ilyas, I.F., Chu, X.: Data Cleaning. ACM, New York (2019)"},{"key":"775_CR75","doi-asserted-by":"crossref","unstructured":"Ilyas, I.F., Rekatsinas, T.: Machine learning and data cleaning: Which serves the other? J. Data Inf. Qual. (2021). Just Accepted","DOI":"10.1145\/3506712"},{"key":"775_CR76","doi-asserted-by":"crossref","unstructured":"Iosifidis, V., Ntoutsi, E.: Adafair: cumulative fairness adaptive boosting. In: CIKM, pp. 781\u2013790 (2019)","DOI":"10.1145\/3357384.3357974"},{"key":"775_CR77","unstructured":"Jiang, H., Nachum, O.: Identifying and correcting label bias in machine learning. In: AISTATS, pp. 702\u2013712 (2020)"},{"key":"775_CR78","unstructured":"Jiang, L., Zhou, Z., Leung, T., Li, L.-J., Fei-Fei, L.: Mentornet: learning data-driven curriculum for very deep neural networks on corrupted labels. In: ICML, pp. 2309\u20132318 (2018)"},{"key":"775_CR79","unstructured":"Kaggle. https:\/\/www.kaggle.com"},{"issue":"1","key":"775_CR80","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-011-0463-8","volume":"33","author":"F Kamiran","year":"2011","unstructured":"Kamiran, F., Calders, T.: Data preprocessing techniques for classification without discrimination. Knowl. Inf. Syst. 33(1), 1\u201333 (2011)","journal-title":"Knowl. Inf. Syst."},{"key":"775_CR81","doi-asserted-by":"crossref","unstructured":"Kamishima, T., Akaho, S., Asoh, H., Sakuma, J.: Fairness-aware classifier with prejudice remover regularizer. In: ECML PKDD, pp. 35\u201350 (2012)","DOI":"10.1007\/978-3-642-33486-3_3"},{"issue":"3","key":"775_CR82","doi-asserted-by":"publisher","first-page":"255","DOI":"10.14778\/3430915.3430917","volume":"14","author":"B Karlas","year":"2020","unstructured":"Karlas, B., Li, P., Wu, R., G\u00fcrel, N.M., Chu, X., Wu, W., Zhang, C.: Nearest neighbor classifiers over incomplete information: from certain answers to certain predictions. Proc. VLDB Endow. 14(3), 255\u2013267 (2020)","journal-title":"Proc. VLDB Endow."},{"key":"775_CR83","doi-asserted-by":"crossref","unstructured":"Khademi, A., Lee, S., Foley, D., Honavar, V.: Fairness in algorithmic decision making: an excursion through the lens of causality. In: WWW, pp. 2907\u20132914 (2019)","DOI":"10.1145\/3308558.3313559"},{"key":"775_CR84","doi-asserted-by":"crossref","unstructured":"Khani, F., Liang, P.: Removing spurious features can hurt accuracy and affect groups disproportionately. In: FAccT, pp. 196\u2013205. ACM (2021)","DOI":"10.1145\/3442188.3445883"},{"key":"775_CR85","unstructured":"Kilbertus, N., Rojas-Carulla, M., Parascandolo, G., Hardt, M., Janzing, D., Sch\u00f6lkopf, B.: Avoiding discrimination through causal reasoning. In: NeurIPS, pp. 656\u2013666 (2017)"},{"key":"775_CR86","doi-asserted-by":"crossref","unstructured":"Kim, H., Lee, K., Hwang, G., Suh, C.: Crash to not crash: learn to identify dangerous vehicles using a simulator. In: AAAI, pp. 978\u2013985 (2019)","DOI":"10.1609\/aaai.v33i01.3301978"},{"key":"775_CR87","unstructured":"Koh, P.W., Steinhardt, J., Liang, P.: Stronger data poisoning attacks break data sanitization defenses. CoRR arXiv:1811.00741 (2018)"},{"issue":"12","key":"775_CR88","first-page":"948","volume":"9","author":"S Krishnan","year":"2016","unstructured":"Krishnan, S., Wang, J., Eugene, W., Franklin, M.J., Goldberg, K.: Activeclean: interactive data cleaning for statistical modeling. PVLDB 9(12), 948\u2013959 (2016)","journal-title":"PVLDB"},{"key":"775_CR89","unstructured":"Kurach, K., Lucic, M., Zhai, X., Michalski, M., Gelly, S.: The GAN landscape: losses, architectures, regularization, and normalization. CoRR arXiv:1807.04720 (2018)"},{"key":"775_CR90","unstructured":"Kusner, M.J., Loftus, J., Russell, C., Silva, R.: Counterfactual fairness. In: NeurIPS, pp. 4066\u20134076 (2017)"},{"key":"775_CR91","unstructured":"Lahoti, P., Beutel, A., Chen, J., Lee, K., Prost, F., Thain, N., Wang, X., Chi, E.: Fairness without demographics through adversarially reweighted learning. In: NeurIPS (2020)"},{"key":"775_CR92","unstructured":"Lamy, A.L., Zhong, Z.: Noise-tolerant fair classification. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E.B., Garnett, R. (eds.) NeurIPS, pp. 294\u2013305 (2019)"},{"issue":"3","key":"775_CR93","first-page":"3","volume":"41","author":"DJL Lee","year":"2018","unstructured":"Lee, D.J.L., Parameswaran, A.G.: The case for a visual discovery assistant: a holistic solution for accelerating visual data exploration. IEEE Data Eng. Bull. 41(3), 3\u201314 (2018)","journal-title":"IEEE Data Eng. Bull."},{"key":"775_CR94","doi-asserted-by":"crossref","unstructured":"Lee, J.-G., Roh, Y., Song, H., Whang, S.E.: Machine learning robustness, fairness, and their convergence. In: KDD, pp. 4046\u20134047 (2021)","DOI":"10.1145\/3447548.3470799"},{"key":"775_CR95","unstructured":"Li, J., Socher, R., Hoi, S.C.H.: Dividemix: learning with noisy labels as semi-supervised learning. In: ICLR (2020)"},{"key":"775_CR96","unstructured":"Li, P., Rao, X., Blase, J., Zhang, Y., Chu, X., Zhang, C.: CleanML: a benchmark for joint data cleaning and machine learning [experiments and analysis]. In: ICDE (2021)"},{"key":"775_CR97","unstructured":"Liu, Z., Park, J.H., Rekatsinas, T., Tzamos, C.: On robust mean estimation under coordinate-level corruption. In: ICML, pp. 6914\u20136924. PMLR (2021)"},{"key":"775_CR98","unstructured":"Liu, Z., Park, J., Rekatsinas, T., Tzamos, C.: On robust mean estimation under coordinate-level corruption. In: ICML, pp. 6914\u20136924 (2021)"},{"key":"775_CR99","unstructured":"Malach, E., Shalev-Shwartz, S.: Decoupling \u201cwhen to update\u201d from \u201chow to update\u201d. In: NIPS, pp. 960\u2013970 (2017)"},{"key":"775_CR100","unstructured":"Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. CoRR arXiv:1908.09635 (2019)"},{"key":"775_CR101","unstructured":"Melgar, L.A., Dao, D., Gan, S., G\u00fcrel, N.M., Hollenstein, N., Jiang, J., Karlas, B., Lemmin, T., Li, T., Li, Y., Rao, X., Rausch, J., Renggli, C., Rimanic, L., Weber, M., Zhang, S., Zhao, Z., Schawinski, K., Wu, W., Zhang, C.: Ease.ml: a lifecycle management system for machine learning. In: CIDR (2021)"},{"key":"775_CR102","doi-asserted-by":"crossref","unstructured":"Meng, D., Chen, H.: Magnet: a two-pronged defense against adversarial examples. In: Thuraisingham, B.M., Evans, D., Malkin, T., Xu, D. (eds.) ACM SIGSAC, pp. 135\u2013147 (2017)","DOI":"10.1145\/3133956.3134057"},{"key":"775_CR103","unstructured":"Metzen, J.H., Genewein, T., Fischer, V., Bischoff, B.: On detecting adversarial perturbations. In: ICLR (2017)"},{"issue":"2","key":"775_CR104","first-page":"59","volume":"41","author":"RJ Miller","year":"2018","unstructured":"Miller, R.J., Nargesian, F., Zhu, E., Christodoulakis, C., Pu, K.Q., Andritsos, P.: Making open data transparent: data discovery on open data. IEEE Data Eng. Bull. 41(2), 59\u201370 (2018)","journal-title":"IEEE Data Eng. Bull."},{"key":"775_CR105","doi-asserted-by":"crossref","unstructured":"Mintz, M., Bills, S., Snow, R., Jurafsky, D.: Distant supervision for relation extraction without labeled data. In: Su, K.-Y., Su, J., Wiebe, J. (eds.) ACL, pp. 1003\u20131011 (2009)","DOI":"10.3115\/1690219.1690287"},{"key":"775_CR106","doi-asserted-by":"crossref","unstructured":"Nabi, R., Shpitser, I.: Fair inference on outcomes. In: AAAI, pp. 1931\u20131940 (2018)","DOI":"10.1609\/aaai.v32i1.11553"},{"issue":"1","key":"775_CR107","first-page":"24","volume":"44","author":"F Neutatz","year":"2021","unstructured":"Neutatz, F., Chen, B., Abedjan, Z., Eugene, W.: From cleaning before ML to cleaning for ML. IEEE Data Eng. Bull. 44(1), 24\u201341 (2021)","journal-title":"IEEE Data Eng. Bull."},{"key":"775_CR108","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: ECCV, pp. 69\u201384 (2016)","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"775_CR109","unstructured":"Principles for AI ethics. https:\/\/research.samsung.com\/artificial-intelligence. Accessed 13 July 2022"},{"issue":"10","key":"775_CR110","first-page":"1345","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE TKDE 22(10), 1345\u20131359 (2010)","journal-title":"IEEE TKDE"},{"key":"775_CR111","doi-asserted-by":"crossref","unstructured":"Papernot, N., McDaniel, P.D., Wu, X., Jha, S., Swami, A.: Distillation as a defense to adversarial perturbations against deep neural networks. In: IEEE SP, pp. 582\u2013597 (2016)","DOI":"10.1109\/SP.2016.41"},{"key":"775_CR112","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., Chintala, S.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) NeurIPS, pp. 8024\u20138035. Curran Associates, Inc. (2019)"},{"key":"775_CR113","doi-asserted-by":"crossref","unstructured":"Patrini, G., Rozza, A., Menon, A.K., Nock, R., Qu, L.: Making deep neural networks robust to label noise: a loss correction approach. In: CVPR, pp. 2233\u20132241 (2017)","DOI":"10.1109\/CVPR.2017.240"},{"key":"775_CR114","unstructured":"Paudice, A., Mu\u00f1oz-Gonz\u00e1lez, L., Gy\u00f6rgy, A., Lupu, E.C.: Detection of adversarial training examples in poisoning attacks through anomaly detection. CoRR arXiv:1802.03041 (2018)"},{"key":"775_CR115","doi-asserted-by":"crossref","unstructured":"Pelekis, N., Ntrigkogias, C., Tampakis, P., Sideridis, S., Theodoridis, Y.: Hermoupolis: a trajectory generator for simulating generalized mobility patterns. In: ECML PKDD, pp. 659\u2013662 (2013)","DOI":"10.1007\/978-3-642-40994-3_49"},{"key":"775_CR116","unstructured":"Pleiss, G., Raghavan, M., Wu, F., Kleinberg, J.M., Weinberger, K.Q.: On fairness and calibration. In: NIPS, pp. 5680\u20135689 (2017)"},{"key":"775_CR117","doi-asserted-by":"crossref","unstructured":"Polyzotis, N., Roy, S., Whang, S.E., Zinkevich, M.: Data management challenges in production machine learning. In: SIGMOD, pp. 1723\u20131726 (2017)","DOI":"10.1145\/3035918.3054782"},{"issue":"2","key":"775_CR118","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1145\/3299887.3299891","volume":"47","author":"N Polyzotis","year":"2018","unstructured":"Polyzotis, N., Roy, S., Whang, S.E., Zinkevich, M.: Data lifecycle challenges in production machine learning: a survey. SIGMOD Rec. 47(2), 17\u201328 (2018)","journal-title":"SIGMOD Rec."},{"key":"775_CR119","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/RBME.2020.3013489","volume":"14","author":"A Qayyum","year":"2020","unstructured":"Qayyum, A., Qadir, J., Bilal, M., Al-Fuqaha, A.: Secure and robust machine learning for healthcare: a survey. IEEE Rev. Biomed. Eng. 14, 156\u2013180 (2020)","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"775_CR120","unstructured":"Responsible AI practices. https:\/\/ai.google\/responsibilities\/responsible-ai-practices. Accessed 13 July 2022"},{"key":"775_CR121","unstructured":"Responsible AI principles from Microsoft. https:\/\/www.microsoft.com\/en-us\/ai\/responsible-ai. Accessed 13 July 2022"},{"issue":"3","key":"775_CR122","first-page":"269","volume":"11","author":"A Ratner","year":"2017","unstructured":"Ratner, A., Bach, S.H., Ehrenberg, H., Fries, J., Sen, W., R\u00e9, C.: Snorkel: rapid training data creation with weak supervision. PVLDB 11(3), 269\u2013282 (2017)","journal-title":"PVLDB"},{"issue":"2\u20133","key":"775_CR123","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/s00778-019-00552-1","volume":"29","author":"A Ratner","year":"2020","unstructured":"Ratner, A., Bach, S.H., Ehrenberg, H.R., Fries, J.A., Sen, W., R\u00e9, C.: Snorkel: rapid training data creation with weak supervision. VLDB J. 29(2\u20133), 709\u2013730 (2020)","journal-title":"VLDB J."},{"key":"775_CR124","unstructured":"Ratner, A.J., Ehrenberg, H.R., Hussain, Z., Dunnmon, J., R\u00e9, C.: Learning to compose domain-specific transformations for data augmentation. In: NIPS, pp. 3239\u20133249 (2017)"},{"key":"775_CR125","unstructured":"Redyuk, S., Kaoudi, Z., Markl, V., Schelter, S.: Automating data quality validation for dynamic data ingestion. In: EDBT, pp. 61\u201372 (2021)"},{"key":"775_CR126","unstructured":"Reed, S.E., Lee, H., Anguelov, D., Szegedy, C., Erhan, D., Rabinovich, A.: Training deep neural networks on noisy labels with bootstrapping. In: ICLR (2015)"},{"issue":"11","key":"775_CR127","first-page":"1190","volume":"10","author":"T Rekatsinas","year":"2017","unstructured":"Rekatsinas, T., Chu, X., Ilyas, I.F., R\u00e9, C.: Holoclean: holistic data repairs with probabilistic inference. PVLDB 10(11), 1190\u20131201 (2017)","journal-title":"PVLDB"},{"issue":"1","key":"775_CR128","first-page":"11","volume":"44","author":"C Renggli","year":"2021","unstructured":"Renggli, C., Rimanic, L., G\u00fcrel, N.M., Karlas, B., Wu, W., Zhang, C.: A data quality-driven view of mlops. IEEE Data Eng. Bull. 44(1), 11\u201323 (2021)","journal-title":"IEEE Data Eng. Bull."},{"key":"775_CR129","volume-title":"Recommender Systems Handbook","year":"2015","unstructured":"Ricci, F., Rokach, L., Shapira, B. (eds.): Recommender Systems Handbook. Springer, Berlin (2015)"},{"key":"775_CR130","unstructured":"Roh, Y., Heo, G., Whang, S.E.: A survey on data collection for machine learning: a big data\u2014AI integration perspective. In: IEEE TKDE (2019)"},{"key":"775_CR131","unstructured":"Roh, Y., Lee, K., Whang, S.E., Suh, C.: FR-Train: a mutual information-based approach to fair and robust training. In: ICML (2020)"},{"key":"775_CR132","unstructured":"Roh, Y., Lee, K., Whang, S.E., Suh, C.: Fairbatch: batch selection for model fairness. In: ICLR. OpenReview.net (2021)"},{"key":"775_CR133","unstructured":"Roh, Y., Lee, K., Whang, S.E., Suh, C.: Sample selection for fair and robust training. In: NeurIPS (2021)"},{"key":"775_CR134","unstructured":"Software 2.0. https:\/\/medium.com\/@karpathy\/software-2-0-a64152b37c35"},{"key":"775_CR135","unstructured":"South Korean AI chatbot pulled from Facebook after hate speech towards minorities. https:\/\/www.theguardian.com\/world\/2021\/jan\/14\/time-to-properly-socialise-hate-speech-ai-chatbot-pulled-from-facebook. Accessed 13 July 2022"},{"key":"775_CR136","doi-asserted-by":"crossref","unstructured":"Salimi, B., Rodriguez, L., Howe, B., Suciu, D.: Interventional fairness: causal database repair for algorithmic fairness. In: SIGMOD, pp. 793\u2013810 (2019)","DOI":"10.1145\/3299869.3319901"},{"key":"775_CR137","unstructured":"Schelter, S., B\u00f6se, J.-H., Kirschnick, J., Klein, T., Seufert, S.: Automatically tracking metadata and provenance of machine learning experiments. In: Workshop on ML Systems at NIPS (2017)"},{"key":"775_CR138","doi-asserted-by":"crossref","unstructured":"Schelter, S., Grafberger, S., Schmidt, P., Rukat, T., Kie\u00dfling, M., Taptunov, A., Bie\u00dfmann, F., Lange, D.: Differential data quality verification on partitioned data. In: ICDE, pp. 1940\u20131945 (2019)","DOI":"10.1109\/ICDE.2019.00210"},{"issue":"12","key":"775_CR139","doi-asserted-by":"publisher","first-page":"1781","DOI":"10.14778\/3229863.3229867","volume":"11","author":"S Schelter","year":"2018","unstructured":"Schelter, S., Lange, D., Schmidt, P., Celikel, M., Bie\u00dfmann, F., Grafberger, A.: Automating large-scale data quality verification. Proc. VLDB Endow. 11(12), 1781\u20131794 (2018)","journal-title":"Proc. VLDB Endow."},{"key":"775_CR140","unstructured":"Schelter, S., Rukat, T., Biessmann, F.: JENGA: a framework to study the impact of data errors on the predictions of machine learning models. In: EDBT, pp. 529\u2013534 (2021)"},{"key":"775_CR141","unstructured":"Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., Chaudhary, V., Young, M., Crespo, J.-F., Dennison, D.: Hidden technical debt in machine learning systems. In: NIPS, pp. 2503\u20132511 (2015)"},{"key":"775_CR142","doi-asserted-by":"crossref","unstructured":"Settles, B.: Active learning. In: Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers (2012)","DOI":"10.1007\/978-3-031-01560-1"},{"key":"775_CR143","unstructured":"Shafahi, A., Huang, W.R., Najibi, M., Suciu, O., Studer, C., Dumitras, T., Goldstein, T.: Poison frogs! Targeted clean-label poisoning attacks on neural networks. In: NeurIPS, pp. 6106\u20136116 (2018)"},{"issue":"2","key":"775_CR144","first-page":"883","volume":"205","author":"L Shang","year":"2008","unstructured":"Shang, L.: Denoising natural images based on a modified sparse coding algorithm. Appl. Math. Comput. 205(2), 883\u2013889 (2008)","journal-title":"Appl. Math. Comput."},{"key":"775_CR145","unstructured":"Shen, Z., Liu, J., He, Y., Zhang, X., Xu, R., Yu, H., Cui, P.: Towards out-of-distribution generalization: a survey. arXiv:2108.13624 (2021)"},{"key":"775_CR146","doi-asserted-by":"crossref","unstructured":"Sheng, V.S., Provost, F.J., Ipeirotis, P.G.: Get another label? improving data quality and data mining using multiple, noisy labelers. In: KDD, pp. 614\u2013622 (2008)","DOI":"10.1145\/1401890.1401965"},{"key":"775_CR147","unstructured":"Sinha, A., Namkoong, H., Duchi, J.C.: Certifying some distributional robustness with principled adversarial training. In: ICLR (2018)"},{"key":"775_CR148","doi-asserted-by":"crossref","unstructured":"Solans, D., Biggio, B., Castillo, C.: Poisoning attacks on algorithmic fairness. In: Hutter, F., Kersting, K., Lijffijt, J., Valera, I. (eds.) ECML PKDD, vol. 12457, pp. 162\u2013177. Springer (2020)","DOI":"10.1007\/978-3-030-67658-2_10"},{"key":"775_CR149","unstructured":"Song, H., Kim, M., Lee, J.-G.: SELFIE: refurbishing unclean samples for robust deep learning. In: ICML, pp. 5907\u20135915 (2019)"},{"key":"775_CR150","unstructured":"Song, H., Kim, M., Park, D., Lee, J.-G.: Learning from noisy labels with deep neural networks: a survey. CoRR arXiv:2007.08199 (2020)"},{"key":"775_CR151","doi-asserted-by":"crossref","unstructured":"Song, H., Kim, M., Park, D., Shin, Y., Lee, J.-G.: Robust learning by self-transition for handling noisy labels. In: KDD, pp. 1490\u20131500 (2021)","DOI":"10.1145\/3447548.3467222"},{"issue":"2","key":"775_CR152","first-page":"3","volume":"41","author":"M Stonebraker","year":"2018","unstructured":"Stonebraker, M., Ilyas, I.F.: Data integration: the current status and the way forward. IEEE Data Eng. Bull. 41(2), 3\u20139 (2018)","journal-title":"IEEE Data Eng. Bull."},{"key":"775_CR153","first-page":"3","volume":"42","author":"M Stonebraker","year":"2019","unstructured":"Stonebraker, M., Rezig, E.K.: Machine learning and big data: what is important? IEEE Data Eng. Bull. 42, 3\u20137 (2019)","journal-title":"IEEE Data Eng. Bull."},{"key":"775_CR154","unstructured":"Trusting AI. https:\/\/www.research.ibm.com\/artificial-intelligence\/trusted-ai\/. Accessed 13 July 2022"},{"key":"775_CR155","doi-asserted-by":"crossref","unstructured":"Tae, K.H., Whang, S.E.: Slice tuner: a selective data acquisition framework for accurate and fair machine learning models. In: SIGMOD, pp. 1771\u20131783. ACM (2021)","DOI":"10.1145\/3448016.3452792"},{"key":"775_CR156","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: NIPS, pp. 1195\u20131204 (2017)"},{"key":"775_CR157","unstructured":"Terrizzano, I.G., Schwarz, P.M., Roth, M., Colino, J.E.: Data wrangling: the challenging Yourney from the wild to the lake. In: CIDR (2015)"},{"key":"775_CR158","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: IROS, pp. 23\u201330 (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"775_CR159","doi-asserted-by":"crossref","unstructured":"Tremblay, J., Prakash, A., Acuna, D., Brophy, M., Jampani, V., Anil, C., To, T., Cameracci, E., Boochoon, S., Birchfield, S.: Training deep networks with synthetic data: bridging the reality gap by domain randomization. In: CVPR Workshops, pp. 969\u2013977 (2018)","DOI":"10.1109\/CVPRW.2018.00143"},{"issue":"2","key":"775_CR160","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s10115-013-0706-y","volume":"42","author":"I Triguero","year":"2015","unstructured":"Triguero, I., Garc\u00eda, S., Herrera, F.: Self-labeled techniques for semi-supervised learning: taxonomy, software and empirical study. Knowl. Inf. Syst. 42(2), 245\u2013284 (2015)","journal-title":"Knowl. Inf. Syst."},{"key":"775_CR161","unstructured":"Tukey, J.W.: A survey of sampling from contaminated distributions. In: Contributions to Probability and Statistics, pp. 448\u2013485 (1960)"},{"issue":"3","key":"775_CR162","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v045.i03","volume":"45","author":"S van Buuren","year":"2011","unstructured":"van Buuren, S., Groothuis-Oudshoorn, K.: mice: multivariate imputation by chained equations in r. J. Stat. Softw. 45(3), 1\u201367 (2011)","journal-title":"J. Stat. Softw."},{"issue":"3","key":"775_CR163","doi-asserted-by":"publisher","first-page":"223","DOI":"10.14778\/3291264.3291268","volume":"12","author":"P Varma","year":"2018","unstructured":"Varma, P., R\u00e9, C.: Snuba: automating weak supervision to label training data. Proc. VLDB Endow. 12(3), 223\u2013236 (2018)","journal-title":"Proc. VLDB Endow."},{"issue":"13","key":"775_CR164","first-page":"2182","volume":"8","author":"M Vartak","year":"2015","unstructured":"Vartak, M., Rahman, S., Madden, S., Parameswaran, A.G., Polyzotis, N.: SEEDB: efficient data-driven visualization recommendations to support visual analytics. PVLDB 8(13), 2182\u20132193 (2015)","journal-title":"PVLDB"},{"key":"775_CR165","doi-asserted-by":"crossref","unstructured":"Venkatasubramanian, S.: Algorithmic fairness: measures, methods and representations. In: PODS, p. 481 (2019)","DOI":"10.1145\/3294052.3322192"},{"key":"775_CR166","doi-asserted-by":"crossref","unstructured":"Wang, H., Liu, B., Li, C., Yang, Y., Li, T.: Learning with noisy labels for sentence-level sentiment classification. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1655"},{"key":"775_CR167","doi-asserted-by":"crossref","unstructured":"Wang, J., Liu, Y., Levy, C.: Fair classification with group-dependent label noise. In: Elish, M.C., Isaac, W., Zemel, R.S. (eds.) FAccT, pp. 526\u2013536. ACM (2021)","DOI":"10.1145\/3442188.3445915"},{"key":"775_CR168","unstructured":"Wang, S., Guo, W., Narasimhan, H., Cotter, A., Gupta, M.R., Jordan, M.I.: Robust optimization for fairness with noisy protected groups. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.-F., Lin, H.-T. (eds.) NeurIPS (2020)"},{"issue":"12","key":"775_CR169","doi-asserted-by":"publisher","first-page":"3429","DOI":"10.14778\/3415478.3415562","volume":"13","author":"SE Whang","year":"2020","unstructured":"Whang, S.E., Lee, J.-G.: Data collection and quality challenges for deep learning. Proc. VLDB Endow. 13(12), 3429\u20133432 (2020)","journal-title":"Proc. VLDB Endow."},{"issue":"1","key":"775_CR170","first-page":"66","volume":"44","author":"D Xin","year":"2021","unstructured":"Xin, D., Petersohn, D., Tang, D., Yifan, W., Gonzalez, J.E., Hellerstein, J.M., Joseph, A.D., Parameswaran, A.G.: Enhancing the interactivity of dataframe queries by leveraging think time. IEEE Data Eng. Bull. 44(1), 66\u201378 (2021)","journal-title":"IEEE Data Eng. Bull."},{"key":"775_CR171","doi-asserted-by":"crossref","unstructured":"Xu, D., Yuan, S., Zhang, L., Wu, X.: Fairgan: fairness-aware generative adversarial networks. In: IEEE Big Data, pp. 570\u2013575 (2018)","DOI":"10.1109\/BigData.2018.8622525"},{"key":"775_CR172","unstructured":"Xu, H., Liu, X., Li, Y., Jain, A.K., Tang, J.: To be robust or to be fair: towards fairness in adversarial training. In: Meila, M., Zhang, T. (eds.) ICML, vol. 139, pp. 11492\u201311501. PMLR (2021)"},{"key":"775_CR173","doi-asserted-by":"crossref","unstructured":"Xu, W., Evans, D., Qi, Y.: Feature squeezing: detecting adversarial examples in deep neural networks. In: NDSS (2018)","DOI":"10.14722\/ndss.2018.23198"},{"key":"775_CR174","doi-asserted-by":"crossref","unstructured":"Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In: ACL, pp. 189\u2013196, Stroudsburg, PA, USA (1995). Association for Computational Linguistics","DOI":"10.3115\/981658.981684"},{"key":"775_CR175","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Chun, S., Oh, S.J., Yoo, Y., Choe, J.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: ICCV, pp. 6022\u20136031 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"775_CR176","doi-asserted-by":"crossref","unstructured":"Zafar, M.B., Valera, I., Gomez-Rodriguez, M., Gummadi, K.P.: Fairness beyond disparate treatment & disparate impact: learning classification without disparate mistreatment. In: WWW, pp. 1171\u20131180. ACM (2017)","DOI":"10.1145\/3038912.3052660"},{"key":"775_CR177","unstructured":"Zafar, M.B., Valera, I., Gomez-Rodriguez, M., Gummadi, K.P.: Fairness constraints: mechanisms for fair classification. In: AISTATS, pp. 962\u2013970 (2017)"},{"key":"775_CR178","doi-asserted-by":"crossref","unstructured":"Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning. In: AIES, pp. 335\u2013340 (2018)","DOI":"10.1145\/3278721.3278779"},{"key":"775_CR179","doi-asserted-by":"crossref","unstructured":"Zhang, H., Chu, X., Asudeh, A., Navathe, S.B.: Omnifair: a declarative system for model-agnostic group fairness in machine learning. In: SIGMOD, pp. 2076\u20132088 (2021)","DOI":"10.1145\/3448016.3452787"},{"key":"775_CR180","unstructured":"Zhang, H., Davidson, I.: Facct. pp. 138\u2013148. ACM (2021)"},{"key":"775_CR181","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: ICLR (2018)"},{"key":"775_CR182","doi-asserted-by":"crossref","unstructured":"Zhang, J., Bareinboim, E.: Fairness in decision-making: the causal explanation formula. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11564"},{"key":"775_CR183","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Ives, Z.G.: Finding related tables in data lakes for interactive data science. In: SIGMOD, pp. 1951\u20131966 (2020)","DOI":"10.1145\/3318464.3389726"},{"key":"775_CR184","doi-asserted-by":"crossref","unstructured":"Zhao, Z., De Stefani, L., Zgraggen, E., Binnig, C., Upfal, E., Kraska, T.: Controlling false discoveries during interactive data exploration. In: SIGMOD, pp. 527\u2013540 (2017)","DOI":"10.1145\/3035918.3064019"},{"key":"775_CR185","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Goldman, S.A.: Democratic co-learning. In: IEEE ICTAI, pp. 594\u2013602 (2004)","DOI":"10.1109\/ICTAI.2004.48"},{"issue":"11","key":"775_CR186","first-page":"1529","volume":"17","author":"Z-H Zhou","year":"2005","unstructured":"Zhou, Z.-H., Li, M.: Tri-training: exploiting unlabeled data using three classifiers. IEEE TKDE 17(11), 1529\u20131541 (2005)","journal-title":"IEEE TKDE"},{"key":"775_CR187","unstructured":"Zhu, C., Ronny Huang, W., Li, H., Taylor, G., Studer, C., Goldstein, T.: Transferable clean-label poisoning attacks on deep neural nets. In: ICML, pp. 7614\u20137623 (2019)"},{"key":"775_CR188","unstructured":"Zhu, X.: Semi-supervised learning literature survey. Technical report, Computer Sciences, University of Wisconsin-Madison (2005)"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-022-00775-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00778-022-00775-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-022-00775-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T10:15:39Z","timestamp":1728641739000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00778-022-00775-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,3]]},"references-count":188,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["775"],"URL":"https:\/\/doi.org\/10.1007\/s00778-022-00775-9","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,3]]},"assertion":[{"value":"12 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}