{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T16:02:45Z","timestamp":1788278565078,"version":"build-2803163510"},"reference-count":36,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Key R &amp; D Program of China","award":["2018YFC0809800"],"award-info":[{"award-number":["2018YFC0809800"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Error detection is a critical step in data cleaning. Most traditional error detection methods are based on rules and external information with high cost, especially when dealing with large-scaled data. Recently, with the advances of deep learning, some researchers focus their attention on learning the semantic distribution of data for error detection; however, the low error rate in real datasets makes it hard to collect negative samples for training supervised deep learning models. Most of the existing deep-learning-based error detection algorithms solve the class imbalance problem by data augmentation. Due to the inadequate sampling of negative samples, the features learned by those methods may be biased. In this paper, we propose an AEGAN (Auto-Encoder Generative Adversarial Network)-based deep learning model named SAT-GAN (Self-Attention Generative Adversarial Network) to detect errors in relational datasets. Combining the self-attention mechanism with the pre-trained language model, our model can capture semantic features of the dataset, specifically the functional dependency between attributes, so that no rules or constraints are needed for SAT-GAN to identify inconsistent data. For the lack of negative samples, we propose to train our model via zero-shot learning. As a clean-data tailored model, SAT-GAN tries to recognize error data as outliers by learning the latent features of clean data. In our evaluation, SAT-GAN achieves an average F1-score of 0.95 on five datasets, which yields at least 46.2% F1-score improvement over rule-based methods and outperforms state-of-the-art deep learning approaches in the absence of rules and negative samples.<\/jats:p>","DOI":"10.3390\/e24070936","type":"journal-article","created":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T09:41:10Z","timestamp":1657100470000},"page":"936","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Detecting Errors with Zero-Shot Learning"],"prefix":"10.3390","volume":"24","author":[{"given":"Xiaoyu","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China"},{"name":"Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China"},{"name":"Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,7,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ziekow, H., and Ivantysynova, L. (2008, January 7\u201312). A probabilistic approach for cleaning RFID data. Proceedings of the 2008 IEEE 24th International Conference on Data Engineering Workshop, Cancun, Mexico.","DOI":"10.1109\/ICDEW.2008.4498297"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Heidari, A., McGrath, J., Ilyas, I.F., and Rekatsinas, T. (2019, January 30). Holodetect: Few-shot learning for error detection. Proceedings of the 2019 International Conference on Management of Data, Amsterdam, The Netherlands.","DOI":"10.1145\/3299869.3319888"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Luo, J., Xu, Y., Tang, C., and Lv, J. (2017). Learning inverse mapping by autoencoder based generative adversarial nets. Proceedings of the International Conference on Neural Information Processing, Long Beach, CA, USA, 4\u20139 December 2017, Springer.","DOI":"10.1007\/978-3-319-70096-0_22"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Gokhale, C., Das, S., Doan, A., Naughton, J.F., Rampalli, N., Shavlik, J., and Zhu, X. (2014, January 22\u201327). Corleone: Hands-off crowdsourcing for entity matching. Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data, Snowbird, UT, USA.","DOI":"10.1145\/2588555.2588576"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"993","DOI":"10.14778\/2994509.2994518","article-title":"Detecting data errors: Where are we and what needs to be done?","volume":"9","author":"Abedjan","year":"2016","journal-title":"Proc. VLDB Endow."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1412331.1412337","article-title":"Conditional functional dependencies for capturing data inconsistencies","volume":"33","author":"Fan","year":"2008","journal-title":"ACM Trans. Database Syst. (TODS)"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1387","DOI":"10.14778\/3236187.3236193","article-title":"Explaining repaired data with CFDs","volume":"11","author":"Rammelaere","year":"2018","journal-title":"Proc. VLDB Endow."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Rekatsinas, T., Chu, X., Ilyas, I.F., and R\u00e9, C. (2017). HoloClean: Holistic Data Repairs with Probabilistic Inference. Proc. VLDB Endow., 10.","DOI":"10.14778\/3137628.3137631"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1498","DOI":"10.14778\/2536258.2536262","article-title":"Discovering denial constraints","volume":"6","author":"Chu","year":"2013","journal-title":"Proc. VLDB Endow."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hao, S., Tang, N., Li, G., and Li, J. (2017, January 19\u201322). Cleaning relations using knowledge bases. Proceedings of the 2017 IEEE 33rd International Conference on Data Engineering (ICDE), San Diego, CA, USA.","DOI":"10.1109\/ICDE.2017.141"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chu, X., Morcos, J., Ilyas, I.F., Ouzzani, M., Papotti, P., Tang, N., and Ye, Y. (2015, January 31). Katara: A data cleaning system powered by knowledge bases and crowdsourcing. Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, VIC, Australia.","DOI":"10.1145\/2723372.2749431"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Mahdavi, M., Abedjan, Z., Fernandez, R.C., Madden, S., Ouzzani, M., Stonebraker, M., and Tang, N. (2019, January 30\u201331). Raha: A configuration-free error detection system. Proceedings of the 2019 International Conference on Management of Data, Changsha, China.","DOI":"10.1145\/3299869.3324956"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.artint.2012.06.001","article-title":"YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia","volume":"194","author":"Hoffart","year":"2013","journal-title":"Artif. Intell."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"167","DOI":"10.3233\/SW-140134","article-title":"Dbpedia\u2013a large-scale, multilingual knowledge base extracted from wikipedia","volume":"6","author":"Lehmann","year":"2015","journal-title":"Semant. Web"},{"key":"ref_15","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_16","unstructured":"Sanh, V., Debut, L., Chaumond, J., and Wolf, T. (2019). DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter. arXiv."},{"key":"ref_17","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., and Soricut, R. (2019). Albert: A lite bert for self-supervised learning of language representations. arXiv."},{"key":"ref_18","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., and Dai, J. (2020). Deformable detr: Deformable transformers for end-to-end object detection. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23\u201328). End-to-end object detection with transformers. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_20","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Schlegl, T., Seebck, P., Waldstein, S.M., Schmidt-Erfurth, U., and Langs, G. (2017, January 3\u20138). Unsupervised anomaly Detection with generative edversarial networks to guide marker discovery. Proceedings of the International Conference on Information Processing in Medical Imaging, Kloster Irsee, Germany.","DOI":"10.1007\/978-3-319-59050-9_12"},{"key":"ref_22","unstructured":"Zenati, H., Foo, C.S., Lecouat, B., Manek, G., and Chandrasekhar, V.R. (2018). Efficient GAN-Based Anomaly Detection. arXiv."},{"key":"ref_23","unstructured":"Donahue, J., Krhenb\u00fchl, P., and Darrell, T. (2016). Adversarial Feature Learning. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Joulin, A., Grave, E., Bojanowski, P., and Mikolov, T. (2016). Bag of tricks for efficient text classification. arXiv.","DOI":"10.18653\/v1\/E17-2068"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1162\/tacl_a_00051","article-title":"Enriching word vectors with subword information","volume":"5","author":"Bojanowski","year":"2017","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Deng, X., Sun, H., Lees, A., Wu, Y., and Yu, C. (2020). Turl: Table understanding through representation learning. arXiv.","DOI":"10.14778\/3430915.3430921"},{"key":"ref_27","unstructured":"Chen, Y. (2015). Convolutional Neural Network for Sentence Classification. [Master\u2019s Thesis, University of Waterloo]."},{"key":"ref_28","first-page":"3","article-title":"Data cleaning: Problems and current approaches","volume":"23","author":"Rahm","year":"2000","journal-title":"IEEE Data Eng. Bull."},{"key":"ref_29","unstructured":"Chu, X., Ilyas, I.F., and Papotti, P. (2013, January 8\u201312). Holistic data cleaning: Putting violations into context. Proceedings of the 2013 IEEE 29th International Conference on Data Engineering (ICDE), Brisbane, Australia."},{"key":"ref_30","unstructured":"Li, X., Dong, X.L., Lyons, K., Meng, W., and Srivastava, D. (2015). Truth finding on the deep web: Is the problem solved?. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.14778\/3007263.3007314","article-title":"Magellan: Toward building entity matching management systems over data science stacks","volume":"9","author":"Konda","year":"2016","journal-title":"Proc. VLDB Endow."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"36","DOI":"10.14778\/2850578.2850579","article-title":"Messing up with BART: Error generation for evaluating data-cleaning algorithms","volume":"9","author":"Arocena","year":"2015","journal-title":"Proc. VLDB Endow."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C. (2017). An introduction to outlier analysis. Outlier Analysis, Springer.","DOI":"10.1007\/978-3-319-47578-3"},{"key":"ref_34","unstructured":"Micenkov\u00e1, B., McWilliams, B., and Assent, I. (2015). Learning representations for outlier detection on a budget. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1109\/TKDE.2019.2905548","article-title":"Cleaning data with forbidden itemsets","volume":"32","author":"Rammelaere","year":"2019","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"102460","DOI":"10.1016\/j.jnca.2019.102460","article-title":"Network anomaly detection based on logistic regression of nonlinear chaotic invariants","volume":"148","author":"Palmieri","year":"2019","journal-title":"J. Netw. Comput. Appl."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/24\/7\/936\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:43:25Z","timestamp":1760139805000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/24\/7\/936"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":36,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["e24070936"],"URL":"https:\/\/doi.org\/10.3390\/e24070936","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,6]]}}}