{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T10:03:13Z","timestamp":1774605793165,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:00:00Z","timestamp":1771891200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:00:00Z","timestamp":1771891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009827","name":"Alexandria University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100009827","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Deep learning for tabular data presents unique challenges compared to structured data like images or text due to the diversity in feature types, complex relationships between variables, and the frequent occurrence of missing values. Traditional machine learning models like decision trees, random forests, and gradient boosting methods have been more successful on tabular data compared to neural networks, which often require more effort due to weak inductive bias, difficulty capturing heterogeneous feature interactions, and sensitivity to limited or imbalanced samples; but deep learning techniques are evolving to address these limitations. In the literature, TabNet is a deep learning architecture designed specifically for tabular data. It employs attention mechanisms to focus on the most relevant features at each decision step, mimicking how tree-based models like gradient boosting trees work. This research introduces an enhanced TabNet-based model, called CT-TabGAN (Conditional-TabNet GAN), built on the foundation of Tabular Generative Adversarial Network (TGAN) architectures to effectively address class imbalance in tabular datasets. To achieve this, the generator is redesigned to incorporate TabNet-aware feature structuring, allowing for seamless integration into the TabNet training pipeline. Furthermore, the model incorporates an improved conditional sampling module that more effectively preserves the complex dependencies between high-dimensional categorical and continuous features. On benchmark datasets, the proposed CT-TabGAN model consistently outperforms traditional oversampling techniques, achieving F1-scores of 0.93 for Credit Card Fraud Detection, 0.82 for Diabetes Prediction, and 0.92 for Customer Churn while also attaining higher AUC-ROC values of 0.96, 0.88, and 0.95, respectively, demonstrating its superior ability to handle class imbalance in real-world tabular datasets.<\/jats:p>","DOI":"10.1007\/s00607-026-01622-3","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T06:29:30Z","timestamp":1771914570000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CT-TabGAN: enhanced tabular data modeling through conditional generative adversarial networks for imbalance mitigation"],"prefix":"10.1007","volume":"108","author":[{"given":"Saad M.","family":"Darwish","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noha A.","family":"El-Shoafy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,24]]},"reference":[{"issue":"12","key":"1622_CR1","first-page":"1","volume":"56","author":"M Salaheldin Kasem","year":"2024","unstructured":"Salaheldin Kasem M, Abdallah A, Berendeyev A, Elkady E, Mahmoud M, Abdalla M, Hamada M, Vascon S, Nurseitov D, Taj-Eddin I (2024) Deep learning for table detection and structure recognition: A survey. ACM-CSUR 56(12):1\u201341","journal-title":"ACM-CSUR"},{"key":"1622_CR2","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 (2022) Tabular data: deep learning is not all you need. Inform Fusion 81:84\u201390","journal-title":"Inform Fusion"},{"key":"1622_CR3","doi-asserted-by":"crossref","unstructured":"Wen X, Zhang H, Zheng S, Xu W, Bian J From supervised to generative: a novel paradigm for tabular deep learning with large language models. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2024 Aug 25, pp. 3323\u20133333","DOI":"10.1145\/3637528.3671975"},{"issue":"1","key":"1622_CR4","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1186\/s12859-024-05940-1","volume":"25","author":"Y Fan","year":"2024","unstructured":"Fan Y, Waldmann P (2024) Tabular deep learning: a comparative study applied to multi-task genome-wide prediction. BMC Bioinformatics 25(1):322","journal-title":"BMC Bioinformatics"},{"key":"1622_CR5","doi-asserted-by":"crossref","unstructured":"Li Y, Wei Q, Chen X, Li J, Tao C, Xu H (2024 Oct) Improving tabular data extraction in scanned laboratory reports using deep learning models. J Biomed Inform 10:104735","DOI":"10.1016\/j.jbi.2024.104735"},{"issue":"9","key":"1622_CR6","doi-asserted-by":"publisher","first-page":"783","DOI":"10.3390\/e26090783","volume":"26","author":"A Gicic","year":"2024","unstructured":"Gicic A, \u0110onko D, Subasi A (2024) Time sequence deep learning model for ubiquitous tabular data with unique 3D tensors manipulation. Entropy 26(9):783","journal-title":"Entropy"},{"key":"1622_CR7","unstructured":"Cherepanova V, Levin R, Somepalli G, Geiping J, Bruss CB, Wilson AG, Goldstein T, Goldblum M (2024) A performance-driven benchmark for feature selection in tabular deep learning. Adv Neural Inf Process Syst. ;36"},{"issue":"4","key":"1622_CR8","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1177\/00131644231191298","volume":"84","author":"Y Zhen","year":"2024","unstructured":"Zhen Y, Zhu X (2024) An ensemble learning approach based on TabNet and machine learning models for cheating detection in educational tests. Educ Psychol Meas 84(4):780\u2013809","journal-title":"Educ Psychol Meas"},{"issue":"3","key":"1622_CR9","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.3390\/app14031203","volume":"14","author":"H Zhang","year":"2024","unstructured":"Zhang H, Wu Y, Zhang W, Zhang Y (2024) FFNN\u2013TabNet: an enhanced stellar age determination method based on TabNet. Appl Sci 14(3):1203","journal-title":"Appl Sci"},{"key":"1622_CR10","doi-asserted-by":"crossref","unstructured":"Alfares H, Banimelhem O Comparative Analysis of Machine Learning Techniques for Handling Imbalance in IoT- Dataset for Intrusion Detection Systems. In 2024 11th International Conference on Internet of Things: Systems, Management and Security (IOTSMS) 2024 Sep 2, pp. 112\u2013119","DOI":"10.1109\/IOTSMS62296.2024.10710296"},{"key":"1622_CR11","doi-asserted-by":"publisher","first-page":"109726","DOI":"10.1016\/j.compeleceng.2024.109726","volume":"120","author":"A Jaiswal","year":"2024","unstructured":"Jaiswal A, Dwivedi P, Dewang RK (2024) Handling imbalance dataset issue in insider threat detection using machine learning methods. Comput Electr Eng 120:109726","journal-title":"Comput Electr Eng"},{"issue":"10","key":"1622_CR12","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/s10462-024-10884-2","volume":"57","author":"M Salmi","year":"2024","unstructured":"Salmi M, Atif D, Oliva D, Abraham A, Ventura S (2024) Handling imbalanced medical datasets: review of a decade of research. Artif Intell Rev 57(10):273","journal-title":"Artif Intell Rev"},{"key":"1622_CR13","doi-asserted-by":"crossref","unstructured":"Elsoud EA, Hassan M, Alidmat O, Al Henawi E, Alshdaifat N, Igtait M, Ghaben A, Katrawi A, Dmour M (2024) Under sampling techniques for handling unbalanced data with various imbalance rates: A comparative study. Int J Adv Comput Sci Appl. ;15(8)","DOI":"10.14569\/IJACSA.2024.01508124"},{"key":"1622_CR14","unstructured":"Ali M, Ali M, Hussain M, Koundal D Generative adversarial networks (GANs) for medical image processing: recent advancements. Archives Comput Methods Eng 2024 Oct 9:1\u20134"},{"key":"1622_CR15","doi-asserted-by":"crossref","unstructured":"Lim W, Chek KY, Theng LB, Lin CT (2024 Jan) Future of generative adversarial networks (GAN) for anomaly detection in network security: A review. Computers Secur 20:103733","DOI":"10.1016\/j.cose.2024.103733"},{"issue":"1","key":"1622_CR16","first-page":"011001","volume":"5","author":"T Chakraborty","year":"2024","unstructured":"Chakraborty T, KS UR, Naik SM, Panja M, Manvitha B (2024) Ten years of generative adversarial Nets (GANs): a survey of the state-of-the-art. Mach Learning: Sci Technol 5(1):011001","journal-title":"Mach Learning: Sci Technol"},{"key":"1622_CR17","doi-asserted-by":"crossref","unstructured":"Li B, Chen B, Lin N, Yan X, Xie Y, Hao Z (2024) Generating Synthetic Tabular Data by Using Image Generative Adversarial Networks. In Proceedings of the Genetic and Evolutionary Computation Conference Companion. Jul 14 (pp. 1616\u20131622)","DOI":"10.1145\/3638530.3664120"},{"issue":"5","key":"1622_CR18","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.3390\/ma17051142","volume":"17","author":"H Ma","year":"2024","unstructured":"Ma H, Geng M, Wang F, Zheng W, Ai Y, Zhang W (2024) Data augmentation of a corrosion dataset for defect growth prediction of pipelines using conditional tabular generative adversarial networks. Materials 17(5):1142","journal-title":"Materials"},{"issue":"2","key":"1622_CR19","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/s00778-023-00807-y","volume":"33","author":"T Liu","year":"2024","unstructured":"Liu T, Fan J, Li G, Tang N, Du X (2024) Tabular data synthesis with generative adversarial networks: design space and optimizations. VLDB J 33(2):255\u2013280","journal-title":"VLDB J"},{"key":"1622_CR20","unstructured":"Kim DK, Ryu D, Lee Y, Choi DH (2024 Sep) Generative models for tabular data: A review. J Mech Sci Technol 5:1\u20137"},{"issue":"7","key":"1622_CR21","doi-asserted-by":"publisher","first-page":"3112","DOI":"10.3390\/app14073112","volume":"14","author":"Y Liu","year":"2024","unstructured":"Liu Y, Zhou J, Zhang D, Wei S, Yang M, Gao X (2024) Fault diagnosis method of Box-Type substation based on improved conditional tabular generative adversarial network and AlexNet. Appl Sci 14(7):3112","journal-title":"Appl Sci"},{"key":"1622_CR22","unstructured":"Borisov V, Leemann T, Se\u00dfler K, Haug J, Pawelczyk M, Kasneci G (2022) Deep neural networks and tabular data: A survey. IEEE transactions on neural networks and learning systems. Dec 23"},{"key":"1622_CR23","doi-asserted-by":"publisher","first-page":"135392","DOI":"10.1109\/ACCESS.2021.3116481","volume":"9","author":"M Sahakyan","year":"2021","unstructured":"Sahakyan M, Aung Z, Rahwan T (2021) Explainable artificial intelligence for tabular data: A survey. IEEE Access 9:135392\u2013135422","journal-title":"IEEE Access"},{"key":"1622_CR24","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1162\/tacl_a_00544","volume":"11","author":"G Badaro","year":"2023","unstructured":"Badaro G, Saeed M, Papotti P (2023) Transformers for tabular data representation: A survey of models and applications. Trans Association Comput Linguistics 11:227\u2013249","journal-title":"Trans Association Comput Linguistics"},{"issue":"1","key":"1622_CR25","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1186\/s40537-022-00648-6","volume":"9","author":"R Sauber-Cole","year":"2022","unstructured":"Sauber-Cole R, Khoshgoftaar TM (2022) The use of generative adversarial networks to alleviate class imbalance in tabular data: a survey. J Big Data 9(1):98","journal-title":"J Big Data"},{"key":"1622_CR26","unstructured":"Li CT, Tsai YC, Chen CY, Liao JC (2024) Graph neural networks for tabular data learning: A survey with taxonomy and Directions. ArXiv Preprint ArXiv:2401.02143. Jan 4"},{"key":"1622_CR27","doi-asserted-by":"crossref","unstructured":"Habib AZ, Wang K, Hartley MA, Doretto G, Adjeroh DA (2024) TabSeq: A framework for deep learning on tabular data via sequential Ordering. ArXiv Preprint ArXiv:2410.13203. Oct 17","DOI":"10.1007\/978-3-031-78128-5_27"},{"key":"1622_CR28","unstructured":"Gorishniy Y, Rubachev I, Kartashev N, Shlenskii D, Kotelnikov A, Babenko A TabR: Tabular Deep Learning Meets Nearest Neighbors. In The Twelfth International Conference on Learning Representations 2024"},{"key":"1622_CR29","doi-asserted-by":"crossref","unstructured":"Kulkarni AD Fuzzy Convolution Neural Networks for Tabular Data Classification. arXiv preprint arXiv:2406.03506. 2024 Jun 4","DOI":"10.1109\/ACCESS.2024.3479882"},{"key":"1622_CR30","doi-asserted-by":"publisher","first-page":"106180","DOI":"10.1016\/j.neunet.2024.106180","volume":"173","author":"M Villaiz\u00e1n-Vallelado","year":"2024","unstructured":"Villaiz\u00e1n-Vallelado M, Salvatori M, Carro B, Sanchez-Esguevillas AJ (2024) Graph neural network contextual embedding for deep learning on tabular data. Neural Netw 173:106180","journal-title":"Neural Netw"},{"key":"1622_CR31","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1016\/j.future.2024.06.051","volume":"160","author":"T Zoppi","year":"2024","unstructured":"Zoppi T, Gazzini S, Ceccarelli A (2024) Anomaly-based error and intrusion detection in tabular data: no DNN outperforms tree-based classifiers. Future Generation Comput Syst 160:951\u2013965","journal-title":"Future Generation Comput Syst"},{"key":"1622_CR32","doi-asserted-by":"crossref","unstructured":"Yan R, Islam MT, Xing L (2024 Oct) Interpretable discovery of patterns in tabular data via spatially semantic topographic maps. Nat Biomedical Eng 15:1\u20132","DOI":"10.1038\/s41551-024-01268-6"},{"key":"1622_CR33","unstructured":"Kotelnikov A, Baranchuk D, Rubachev I, Babenko A, TABDDPM Modelling tabular data with diffusion models. In International Conference on Machine Learning 2023 Jul 3 (pp. 17564\u201317579). PMLR"},{"issue":"1","key":"1622_CR34","doi-asserted-by":"publisher","first-page":"15267","DOI":"10.1038\/s41598-024-65777-9","volume":"14","author":"F Jia","year":"2024","unstructured":"Jia F, Zhu H, Jia F, Ren X, Chen S, Tan H, Chan WK (2024) A tabular data generation framework guided by downstream tasks optimization. Sci Rep 14(1):15267","journal-title":"Sci Rep"},{"key":"1622_CR35","doi-asserted-by":"publisher","first-page":"121294","DOI":"10.1016\/j.eswa.2023.121294","volume":"237","author":"S Tao","year":"2024","unstructured":"Tao S, Peng P, Li Y, Sun H, Li Q, Wang H (2024) Supervised contrastive representation learning with tree-structured Parzen estimator bayesian optimization for imbalanced tabular data. Expert Syst Appl 237:121294","journal-title":"Expert Syst Appl"},{"key":"1622_CR36","unstructured":"Ye HJ, Yin HH, Zhan DC (2024) Modern neighborhood components analysis: A deep tabular baseline two decades later. arXiv e-prints, pp arXiv\u20132407"},{"key":"1622_CR37","unstructured":"Gorishniy Y, Kotelnikov A, Babenko A (2024) TABM: advancing tabular deep learning with parameter-efficient ensembling. ArXiv Preprint arXiv :241024210"},{"key":"1622_CR38","doi-asserted-by":"publisher","first-page":"110578","DOI":"10.1016\/j.patcog.2024.110578","volume":"154","author":"J Luo","year":"2024","unstructured":"Luo J, Xu S (2024) NCART: neural classification and regression tree for tabular data. Pattern Recogn 154:110578","journal-title":"Pattern Recogn"},{"key":"1622_CR39","unstructured":"Liu SY, Ye HJ (2025) TABPFN unleashed: A scalable and effective solution to tabular classification problems. ArXiv Preprint arXiv :250202527"},{"issue":"3","key":"1622_CR40","doi-asserted-by":"publisher","first-page":"176","DOI":"10.3390\/machines10030176","volume":"10","author":"K Bhavsar","year":"2022","unstructured":"Bhavsar K, Vakharia V, Chaudhari R, Vora J, Pimenov DY, Giasin K (2022) A comparative study to predict bearing degradation using discrete wavelet transform (DWT), tabular generative adversarial networks (TGAN) and machine learning models. Machines 10(3):176","journal-title":"Machines"},{"issue":"21","key":"1622_CR41","doi-asserted-by":"publisher","first-page":"4757","DOI":"10.3390\/ma13214757","volume":"13","author":"A Marani","year":"2020","unstructured":"Marani A, Jamali A, Nehdi ML (2020) Predicting ultra-high-performance concrete compressive strength using tabular generative adversarial networks. Materials 13(21):4757","journal-title":"Materials"},{"key":"1622_CR42","doi-asserted-by":"publisher","first-page":"105308","DOI":"10.1016\/j.engappai.2022.105308","volume":"115","author":"Z He","year":"2022","unstructured":"He Z, Zhou W (2022) Generation of synthetic full-scale burst test data for corroded pipelines using the tabular generative adversarial network. Eng Appl Artif Intell 115:105308","journal-title":"Eng Appl Artif Intell"},{"issue":"10","key":"1622_CR43","doi-asserted-by":"publisher","first-page":"1965","DOI":"10.3390\/electronics13101965","volume":"13","author":"E Papadaki","year":"2024","unstructured":"Papadaki E, Vrahatis AG, Kotsiantis S (2024) Exploring innovative approaches to synthetic tabular data generation. Electronics 13(10):1965","journal-title":"Electronics"},{"issue":"1","key":"1622_CR44","first-page":"76","volume":"9","author":"MA Basri","year":"2024","unstructured":"Basri MA, Hu B, Abdullah AYM, Tsao S-F, Butt Z, Chen H (2024) A hyperparameter tuning framework for tabular synthetic data generation methods. J Comput Vis Imaging Syst 9(1):76\u201379","journal-title":"J Comput Vis Imaging Syst"},{"issue":"23","key":"1622_CR45","doi-asserted-by":"publisher","first-page":"7673","DOI":"10.3390\/s24237673","volume":"24","author":"M Alqulaity","year":"2024","unstructured":"Alqulaity M, Yang P (2024) Enhanced conditional GAN for high quality synthetic tabular data generation in mobile based cardiovascular healthcare. Sensors 24(23):7673","journal-title":"Sensors"},{"issue":"3","key":"1622_CR46","doi-asserted-by":"publisher","first-page":"273","DOI":"10.3390\/sym16030273","volume":"16","author":"Y Chen","year":"2024","unstructured":"Chen Y, Zou J, Liu L, Hu C (2024) Improved oversampling algorithm for imbalanced data based on K-nearest neighbor and interpolation process optimization. Symmetry 16(3):273","journal-title":"Symmetry"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-026-01622-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00607-026-01622-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-026-01622-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T09:32:46Z","timestamp":1774603966000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00607-026-01622-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,24]]},"references-count":46,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["1622"],"URL":"https:\/\/doi.org\/10.1007\/s00607-026-01622-3","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,24]]},"assertion":[{"value":"11 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}],"article-number":"40"}}