{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:05:34Z","timestamp":1743073534445,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031466700"},{"type":"electronic","value":"9783031466717"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-46671-7_12","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T11:02:26Z","timestamp":1699095746000},"page":"167-182","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TabMentor: Detect Errors on\u00a0Tabular Data with\u00a0Noisy Labels"],"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":"Yaoshu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Asif","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Arik, S.\u00d6., Pfister, T.: Tabnet: attentive interpretable tabular learning. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"12_CR2","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":"12_CR3","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"12_CR4","first-page":"1","volume":"20","author":"F Biessmann","year":"2019","unstructured":"Biessmann, F., et al.: Datawig: missing value imputation for tables. J. Mach. Learn. Res. 20, 1\u20136 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"12_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1541880.1541882","volume":"41","author":"V Chandola","year":"2009","unstructured":"Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. (CSUR) 41, 1\u201358 (2009)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"12_CR6","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":"12_CR7","unstructured":"Chu, X., Ilyas, I.F., Papotti, P.: Holistic data cleaning: putting violations into context. In: ICDE. IEEE (2013)"},{"key":"12_CR8","first-page":"205","volume":"1","author":"I Csisz\u00e1r","year":"1984","unstructured":"Csisz\u00e1r, I.: Information geometry and alternating minimization procedures. Stat. Decis. 1, 205\u2013237 (1984)","journal-title":"Stat. Decis."},{"key":"12_CR9","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":"12_CR10","unstructured":"Das, S., Doan, A., Psgc, C.G., Konda, P., Govind, Y., Paulsen, D.: The magellan data repository (2015)"},{"key":"12_CR11","unstructured":"Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"12_CR12","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":"12_CR13","unstructured":"Hellerstein, J.M.: Quantitative data cleaning for large databases. UNECE (2008)"},{"key":"12_CR14","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"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, L., Meng, D., Zhao, Q., Shan, S., Hauptmann, A.G.: Self-paced curriculum learning. In: Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"12_CR16","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":"12_CR17","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":"12_CR18","unstructured":"Katzir, L., Elidan, G., El-Yaniv, R.: Net-dnf: effective deep modeling of tabular data. In: International Conference on Learning Representations (2020)"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Krishnan, S., Wang, J., Wu, E., Franklin, M.J., Goldberg, K.: Activeclean: interactive data cleaning for statistical modeling. In: PVLDB (2016)","DOI":"10.1145\/2882903.2899409"},{"key":"12_CR20","unstructured":"Kumar, M., Packer, B., Koller, D.: Self-paced learning for latent variable models. Adv. Neural Inf. Process. Syst. (2010)"},{"key":"12_CR21","unstructured":"Li, J., Socher, R., Hoi, S.C.: Dividemix: learning with noisy labels as semi-supervised learning. arXiv preprint arXiv:2002.07394 (2020)"},{"key":"12_CR22","unstructured":"Liu, Z., Zhou, Z., Rekatsinas, T.: Picket: self-supervised data diagnostics for ml pipelines. arXiv (2020)"},{"key":"12_CR23","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":"12_CR24","unstructured":"Malach, E., Shalev-Shwartz, S.: Decoupling \u201cwhen to update\u201d from \u201chow to update\". Adv. Neural Inf. Process. Syst. (2017)"},{"key":"12_CR25","unstructured":"Neutatz, F., Chen, B., Abedjan, Z., Wu, E.: From cleaning before ml to cleaning for ml. IEEE (2021)"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Neutatz, F., Mahdavi, M., Abedjan, Z.: Ed2: two-stage active learning for error detection-technical report. arXiv (2019)","DOI":"10.1145\/3357384.3358129"},{"key":"12_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13643-016-0384-4","volume":"5","author":"M Ouzzani","year":"2016","unstructured":"Ouzzani, M., Hammady, H., Fedorowicz, Z., Elmagarmid, A.: Rayyan-a web and mobile app for systematic reviews. Syst. Rev. 5, 1\u201310 (2016)","journal-title":"Syst. Rev."},{"key":"12_CR28","unstructured":"Pit-Claudel, C., Mariet, Z., Harding, R., Madden, S.: Outlier detection in heterogeneous datasets using automatic tuple expansion (2016)"},{"key":"12_CR29","unstructured":"Popov, S., Morozov, S., Babenko, A.: Neural oblivious decision ensembles for deep learning on tabular data. arXiv preprint arXiv:1909.06312 (2019)"},{"key":"12_CR30","unstructured":"Rahm, E., Do, H.H.: Data cleaning: problems and current approaches. IEEE (2000)"},{"key":"12_CR31","unstructured":"Raman, V., Hellerstein, J.M.: Potter\u2019s wheel: an interactive data cleaning system. In: VLDB (2001)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Rammelaere, J., Geerts, F.: Explaining repaired data with cfds. In: VLDB (2018)","DOI":"10.14778\/3236187.3236193"},{"key":"12_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":"12_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":"12_CR35","unstructured":"Rosales, R., Fung, G., Tong, W.: Automatic discrimination of mislabeled training points for large margin classifiers. In: Proceedings of Snowbird Machine Learning Workshop. Citeseer (2009)"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Sambasivan, N., Kapania, S., Highfill, H., Akrong, D., Paritosh, P., Aroyo, L.M.: \u201ceveryone wants to do the model work, not the data work\u201d: data cascades in high-stakes AI. In: proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (2021)","DOI":"10.1145\/3411764.3445518"},{"key":"12_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1007\/978-3-030-58583-9_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Sharma","year":"2020","unstructured":"Sharma, K., Donmez, P., Luo, E., Liu, Y., Yalniz, I.Z.: NoiseRank: unsupervised label noise reduction with dependence models. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 737\u2013753. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58583-9_44"},{"key":"12_CR38","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","volume":"81","author":"R Shwartz-Ziv","year":"2022","unstructured":"Shwartz-Ziv, R., Armon, A.: Tabular data: deep learning is not all you need. Inf. Fusion 81, 84\u201390 (2022)","journal-title":"Inf. Fusion"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Visengeriyeva, L., Abedjan, Z.: Metadata-driven error detection. In: SSDBM (2018)","DOI":"10.1145\/3221269.3223028"},{"key":"12_CR40","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":"12_CR41","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":"12_CR42","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":"12_CR43","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning (still) requires rethinking generalization. Commun. ACM 64, 107\u2013115 (2021)","journal-title":"Commun. ACM"},{"key":"12_CR44","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","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46671-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T11:04:13Z","timestamp":1699095853000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46671-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031466700","9783031466717"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46671-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","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":"27 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2023.uqcloud.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes. Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"503","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"216","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"43% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.97","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.77","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}