{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/zgan-an-outlier-focused-generative","title":"zGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generation","arxiv_id":"2410.20808","date":"2024-10-28","proceeding":null,"authors":["Azizjon Azimi","Bonu Boboeva","Ilyas Varshavskiy","Shuhrat Khalilbekov","Akhlitdin Nizamitdinov","Najima Noyoftova","Sergey Shulgin"],"abstract":"The phenomenon of \"black swans\" has posed a fundamental challenge to performance of classical machine learning models. The perceived rise in frequency of outlier conditions, especially in post-pandemic environment, has necessitated exploration of synthetic data as a complement to real data in model training. This article provides a general overview and experimental investigation of the zGAN model architecture developed for the purpose of generating synthetic tabular data with outlier characteristics. The model is put to test in binary classification environments and shows promising results on realistic synthetic data generation, as well as uplift capabilities vis-\\`a-vis model performance. A distinctive feature of zGAN is its enhanced correlation capability between features in the generated data, replicating correlations of features in real training data. Furthermore, crucial is the ability of zGAN to generate outliers based on covariance of real data or synthetically generated covariances. This approach to outlier generation enables modeling of complex economic events and augmentation of outliers for tasks such as training predictive models and detecting, processing or removing outliers. Experiments and comparative analyses as part of this study were conducted on both private (credit risk in financial services) and public datasets.","url_abs":"https://arxiv.org/abs/2410.20808v2","url_pdf":"https://arxiv.org/pdf/2410.20808v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"synthetic-data-evaluation","task_name":"Synthetic Data Evaluation"},{"task_slug":"synthetic-data-generation","task_name":"Synthetic Data Generation"},{"task_slug":"synthetic-outliers-evaluation","task_name":"Synthetic Outliers Evaluation"}],"methods":[{"method_slug":"outlier-generation","method_name":"Outlier Generation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"outlier-generation","name":"Outlier Generation","full_name":"Outlier Generation in Tabular Data"}],"results":[{"leaderboard":"/sota/synthetic-data-evaluation-on-titanic","task":"Synthetic Data Evaluation","dataset":"Titanic","model":"zGAN","rank_in_archive_order":1,"of":7,"metrics":{"AUC":"0.8163"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-data-evaluation-on-titanic","task":"Synthetic Data Evaluation","dataset":"Titanic","model":"CopulaGAN","rank_in_archive_order":2,"of":7,"metrics":{"AUC":"0.8076"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-data-evaluation-on-titanic","task":"Synthetic Data Evaluation","dataset":"Titanic","model":"CTGAN","rank_in_archive_order":3,"of":7,"metrics":{"AUC":"0.7923"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-data-evaluation-on-titanic","task":"Synthetic Data Evaluation","dataset":"Titanic","model":"TVAE","rank_in_archive_order":4,"of":7,"metrics":{"AUC":"0.7874"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-data-evaluation-on-titanic","task":"Synthetic Data Evaluation","dataset":"Titanic","model":"SynthPop","rank_in_archive_order":5,"of":7,"metrics":{"AUC":"0.7861"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-data-evaluation-on-titanic","task":"Synthetic Data Evaluation","dataset":"Titanic","model":"Gaussian Copula","rank_in_archive_order":6,"of":7,"metrics":{"AUC":"0.7846"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-data-evaluation-on-titanic","task":"Synthetic Data Evaluation","dataset":"Titanic","model":"PrivBayes","rank_in_archive_order":7,"of":7,"metrics":{"AUC":"0.534"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-outliers-evaluation-on-a9-3","task":"Synthetic Outliers Evaluation","dataset":"A9 (3% outliers)","model":"zGAN","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"0.7116"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-outliers-evaluation-on-a9-5","task":"Synthetic Outliers Evaluation","dataset":"A9 (5% outliers)","model":"zGAN","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"0.7147"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-outliers-evaluation-on-a9-7-4","task":"Synthetic Outliers Evaluation","dataset":"A9 (7.4% outliers)","model":"zGAN","rank_in_archive_order":1,"of":1,"metrics":{"AUC":"0.7122"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}