{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T23:43:55Z","timestamp":1771890235755,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819724208","type":"print"},{"value":"9789819724215","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-97-2421-5_5","type":"book-chapter","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:01:48Z","timestamp":1715414508000},"page":"63-78","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Adaptive Label Cleaning for\u00a0Error Detection on\u00a0Tabular Data"],"prefix":"10.1007","author":[{"given":"Yaru","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianbin","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaoshu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Asif","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,12]]},"reference":[{"key":"5_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1007\/978-3-540-76298-0_52","volume-title":"The Semantic Web","author":"S Auer","year":"2007","unstructured":"Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: Aberer, K., et al. (eds.) ASWC\/ISWC -2007. LNCS, vol. 4825, pp. 722\u2013735. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-76298-0_52"},{"key":"5_CR2","unstructured":"Biessmann, F., et al.: DataWig: missing value imputation for tables. J. Mach. Learn. Res. 20(175), 1\u20136 (2019)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Bolstad, W.M., Curran, J.M.: Introduction to Bayesian Statistics. Wiley, New York (2016)","DOI":"10.1002\/9781118593165"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Chu, X., Ilyas, I.F., Krishnan, S., Wang, J.: Data cleaning: overview and emerging challenges. In: Proceedings of the 2016 International Conference on Management of Data (2016)","DOI":"10.1145\/2882903.2912574"},{"key":"5_CR5","unstructured":"Chu, X., Ilyas, I.F., Papotti, P.: Holistic data cleaning: putting violations into context. In: ICDE. IEEE (2013)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chu, X., et al.: KATARA: a data cleaning system powered by knowledge bases and crowdsourcing. In: 2015 ACM SIGMOD (2015)","DOI":"10.1145\/2723372.2749431"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Dallachiesa, M., et al.: NADEEF: a commodity data cleaning system. In: 2013 ACM SIGMOD (2013)","DOI":"10.1145\/2463676.2465327"},{"key":"5_CR8","unstructured":"Das, S., Doan, A., Psgc, C.G., Konda, P., Govind, Y., Paulsen, D.: The Magellan data repository (2015)"},{"key":"5_CR9","unstructured":"Deng, D., et al.: The data civilizer system. In: CIDR (2017)"},{"issue":"6","key":"5_CR10","doi-asserted-by":"publisher","first-page":"2429","DOI":"10.1007\/s11280-021-00986-0","volume":"25","author":"I Dimitriadis","year":"2022","unstructured":"Dimitriadis, I., Poiitis, M., Faloutsos, C., Vakali, A.: TG-OUT: temporal outlier patterns detection in Twitter attribute induced graphs. World Wide Web 25(6), 2429\u20132453 (2022)","journal-title":"World Wide Web"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Dolatshah, M.: Cleaning crowdsourced labels using oracles for statistical classification. Ph.D. thesis, Applied Sciences: School of Computing Science (2018)","DOI":"10.14778\/3297753.3297758"},{"key":"5_CR12","unstructured":"Fr\u00e9nay, B., Verleysen, M.: Classification in the presence of label noise: a survey. IEEE (2013)"},{"key":"5_CR13","doi-asserted-by":"publisher","first-page":"2727","DOI":"10.1007\/s11280-023-01160-4","volume":"26","author":"J Fu","year":"2023","unstructured":"Fu, J., Wang, L., Ke, J., Yang, K., Yu, R.: GANAD: a GAN-based method for network anomaly detection. World Wide Web 26, 2727\u20132748 (2023)","journal-title":"World Wide Web"},{"key":"5_CR14","unstructured":"Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Heidari, A., McGrath, J., Ilyas, I.F., Rekatsinas, T.: HoloDetect: few-shot learning for error detection. In: Proceedings of the 2019 International Conference on Management of Data (2019)","DOI":"10.1145\/3299869.3319888"},{"key":"5_CR16","unstructured":"Hellerstein, J.M.: Quantitative data cleaning for large databases. UNECE (2008)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Z., He, Y.: Auto-detect: data-driven error detection in tables. In: Proceedings of the 2018 International Conference on Management of Data (2018)","DOI":"10.1145\/3183713.3196889"},{"issue":"3","key":"5_CR18","doi-asserted-by":"publisher","first-page":"297","DOI":"10.20965\/jaciii.2010.p0297","volume":"14","author":"P Jeatrakul","year":"2010","unstructured":"Jeatrakul, P., Wong, K.W., Fung, C.C.: Data cleaning for classification using misclassification analysis. J. Adv. Comput. Intell. Intell. Inform. 14(3), 297\u2013302 (2010)","journal-title":"J. Adv. Comput. Intell. Intell. Inform."},{"key":"5_CR19","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: International Conference on Machine Learning. PMLR (2018)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Kandel, S., Paepcke, A., Hellerstein, J., Heer, J.: Wrangler: interactive visual specification of data transformation scripts. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (2011)","DOI":"10.1145\/1978942.1979444"},{"key":"5_CR21","first-page":"948","volume":"9","author":"S Krishnan","year":"2016","unstructured":"Krishnan, S., Wang, J., Wu, E., Franklin, M.J., Goldberg, K.: ActiveClean: interactive data cleaning for statistical modeling. PVLDB 9, 948\u2013959 (2016)","journal-title":"PVLDB"},{"key":"5_CR22","unstructured":"Li, J., Socher, R., Hoi, S.C.: DivideMix: learning with noisy labels as semi-supervised learning. arXiv preprint arXiv:2002.07394 (2020)"},{"key":"5_CR23","unstructured":"Liu, Z., Zhou, Z., Rekatsinas, T.: Picket: self-supervised data diagnostics for ML pipelines. arXiv (2020)"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Mahdavi, M., et al.: Raha: a configuration-free error detection system. In: SIGMOD (2019)","DOI":"10.1145\/3299869.3324956"},{"key":"5_CR25","unstructured":"Malach, E., Shalev-Shwartz, S.: Decoupling \u201cwhen to update\u201d from \u201chow to update\u201d. In: Advances in Neural Information Processing Systems (2017)"},{"key":"5_CR26","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-642-02319-4_50","volume-title":"Hybrid Artificial Intelligence Systems","author":"ALB Miranda","year":"2009","unstructured":"Miranda, A.L.B., Garcia, L.P.F., Carvalho, A.C.P.L.F., Lorena, A.C.: Use of classification algorithms in noise detection and elimination. In: Corchado, E., Wu, X., Oja, E., Herrero, \u00c1., Baruque, B. (eds.) HAIS 2009. LNCS (LNAI), vol. 5572, pp. 417\u2013424. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-02319-4_50"},{"key":"5_CR27","unstructured":"Neutatz, F., Chen, B., Abedjan, Z., Wu, E.: From cleaning before ML to cleaning for ML. IEEE (2021)"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Neutatz, F., Mahdavi, M., Abedjan, Z.: ED2: two-stage active learning for error detection\u2013technical report. arXiv (2019)","DOI":"10.1145\/3357384.3358129"},{"key":"5_CR29","unstructured":"Pit-Claudel, C., Mariet, Z., Harding, R., Madden, S.: Outlier detection in heterogeneous datasets using automatic tuple expansion (2016)"},{"key":"5_CR30","unstructured":"Rahm, E., Do, H.H.: Data cleaning: problems and current approaches. IEEE (2000)"},{"key":"5_CR31","unstructured":"Raman, V., Hellerstein, J.M.: Potter\u2019s wheel: an interactive data cleaning system. In: VLDB (2001)"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Rammelaere, J., Geerts, F.: Explaining repaired data with CFDS. VLDB (2018)","DOI":"10.14778\/3236187.3236193"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Rekatsinas, T., Chu, X., Ilyas, I.F., R\u00e9, C.: HoloClean: holistic data repairs with probabilistic inference. arXiv (2017)","DOI":"10.14778\/3137628.3137631"},{"key":"5_CR34","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1016\/j.procs.2021.12.189","volume":"197","author":"F Ridzuan","year":"2022","unstructured":"Ridzuan, F., Zainon, W.M.N.W.: Diagnostic analysis for outlier detection in big data analytics. Procedia Comput. Sci. 197, 685\u2013692 (2022)","journal-title":"Procedia Comput. Sci."},{"key":"5_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s43586-020-00001-2","volume":"1","author":"R van de Schoot","year":"2021","unstructured":"van de Schoot, R., et al.: Bayesian statistics and modelling. Nat. Rev. Methods Primers 1, 1 (2021)","journal-title":"Nat. Rev. Methods Primers"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Sch\u00fctze, H., Manning, C.D., Raghavan, P.: Introduction to Information Retrieval. Cambridge University Press, Cambridge (2008)","DOI":"10.1017\/CBO9780511809071"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Visengeriyeva, L., Abedjan, Z.: Metadata-driven error detection. In: SSDBM (2018)","DOI":"10.1145\/3221269.3223028"},{"issue":"5","key":"5_CR38","doi-asserted-by":"publisher","first-page":"2163","DOI":"10.1007\/s11280-022-01052-z","volume":"25","author":"H Xiang","year":"2022","unstructured":"Xiang, H., Zhang, X.: Edge computing empowered anomaly detection framework with dynamic insertion and deletion schemes on data streams. World Wide Web 25(5), 2163\u20132183 (2022)","journal-title":"World Wide Web"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Yakout, M., Elmagarmid, A.K., Neville, J., Ouzzani, M., Ilyas, I.F.: Guided data repair. arXiv (2011)","DOI":"10.14778\/1952376.1952378"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Yan, J.N., Schulte, O., Zhang, M., Wang, J., Cheng, R.: SCODED: statistical constraint oriented data error detection. In: 2020 ACM SIGMOD (2020)","DOI":"10.1145\/3318464.3380568"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Yuan, B., Chen, J., Zhang, W., Tai, H.S., McMains, S.: Iterative cross learning on noisy labels. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE (2018)","DOI":"10.1109\/WACV.2018.00088"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wu, X.: Class noise vs. attribute noise: a quantitative study. Artif. Intell. Rev. 22, 177\u2013210 (2004)","DOI":"10.1007\/s10462-004-0751-8"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2421-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:03:49Z","timestamp":1715414629000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2421-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819724208","9789819724215"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2421-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"12 May 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apweb-waim2023.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}