{"total":35,"rows":[{"id":"2409.16118","title":"TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models","created":"2024-09-24","cited_by_count":16,"area":null},{"id":"2503.05954","title":"A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyond","created":"2025-03-07","cited_by_count":15,"area":null},{"id":"2406.13012","title":"Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models","created":"2024-06-18","cited_by_count":12,"area":null},{"id":"2406.17673","title":"LaTable: Towards Large Tabular Models","created":"2024-06-25","cited_by_count":8,"area":null},{"id":"2210.03047","title":"Conditional Feature Importance for Mixed Data","created":"2022-10-06","cited_by_count":7,"area":null},{"id":"2404.03506","title":"CountARFactuals -- Generating plausible model-agnostic counterfactual explanations with adversarial random forests","created":"2024-04-04","cited_by_count":5,"area":null},{"id":"2406.01805","title":"TabMDA: Tabular Manifold Data Augmentation for Any Classifier using Transformers with In-context Subsetting","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2508.21146","title":"Privacy Auditing Synthetic Data Release through Local Likelihood Attacks","created":"2025-08-28","cited_by_count":5,"area":null},{"id":"2410.00759","title":"Targeted synthetic data generation for tabular data via hardness characterization","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2509.18014","title":"Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2307.00384","title":"CasTGAN: Cascaded Generative Adversarial Network for Realistic Tabular Data Synthesis","created":"2023-07-01","cited_by_count":3,"area":null},{"id":"2505.21441","title":"Autoencoding Random Forests","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2512.08875","title":"When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation","created":"2025-12-09","cited_by_count":3,"area":null},{"id":"2501.01216","title":"TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer","created":"2025-01-02","cited_by_count":2,"area":null},{"id":"2509.19927","title":"TABFAIRGDT: A Fast Fair Tabular Data Generator using Autoregressive Decision Trees","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2607.03926","title":"TabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data","created":"2026-07-04","cited_by_count":2,"area":null},{"id":"2311.07366","title":"arfpy: A python package for density estimation and generative modeling with adversarial random forests","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2410.01933","title":"TAEGAN: Generating Synthetic Tabular Data For Data Augmentation","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2410.03535","title":"NRGBoost: Energy-Based Generative Boosted Trees","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2503.09453","title":"How Well Does Your Tabular Generator Learn the Structure of Tabular Data?","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2504.20687","title":"What's Wrong with Your Synthetic Tabular Data? Using Explainable AI to Evaluate Generative Models","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2603.15306","title":"xplainfi: Feature Importance and Statistical Inference for Machine Learning in R","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.23016","title":"A Sobering Look at Tabular Data Generation via Probabilistic Circuits","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2507.19700","title":"Disjoint Generation of Synthetic Data","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2508.06647","title":"Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGN","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2508.14936","title":"Can synthetic data reproduce real-world findings in epidemiology? A replication study using adversarial random forests","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2512.22259","title":"Cardiac mortality prediction in patients undergoing PCI based on real and synthetic data","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2601.16083","title":"Probably Approximately Correct Maximum A Posteriori Inference","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.16352","title":"Machine Learning in Epidemiology","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.05317","title":"How important are the genes to explain the outcome - the asymmetric Shapley value as an honest importance metric for high-dimensional features","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.15335","title":"Data Augmentation via Causal-Residual Bootstrapping","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.23465","title":"Machine learning models for estimating counterfactuals in a single-arm inflammatory bowel disease study","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2606.08372","title":"SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2607.00127","title":"A Filtered Mixture-of-Generators for Fully Synthetic Survival Training","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.34349","title":"Fuzzy Distribution Modeling for Synthetic Tabular Data Generation with Causality Preservation","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}