{"total":699,"rows":[{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491,"area":null},{"id":"2209.15421","title":"TabDDPM: Modelling Tabular Data with Diffusion Models","created":"2022-09-30","cited_by_count":377,"area":"diffusion"},{"id":"2210.06280","title":"Language Models are Realistic Tabular Data Generators","created":"2022-10-12","cited_by_count":294,"area":null},{"id":"2310.09656","title":"Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space","created":"2023-10-14","cited_by_count":186,"area":"diffusion"},{"id":"2402.17944","title":"Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey","created":"2024-02-27","cited_by_count":159,"area":null},{"id":"2102.08369","title":"CTAB-GAN: Effective Table Data Synthesizing","created":"2021-02-16","cited_by_count":156,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2302.02041","title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers","created":"2023-02-04","cited_by_count":94,"area":null},{"id":"2210.04018","title":"STaSy: Score-based Tabular data Synthesis","created":"2022-10-08","cited_by_count":86,"area":"diffusion"},{"id":"2304.12654","title":"CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis","created":"2023-04-25","cited_by_count":78,"area":"diffusion"},{"id":"2204.00401","title":"CTAB-GAN+: Enhancing Tabular Data Synthesis","created":"2022-04-01","cited_by_count":70,"area":null},{"id":"2205.03257","title":"Synthetic Data -- what, why and how?","created":"2022-05-06","cited_by_count":67,"area":null},{"id":"2302.12580","title":"Membership Inference Attacks against Synthetic Data through Overfitting Detection","created":"2023-02-24","cited_by_count":66,"area":"safety"},{"id":"2410.20626","title":"TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation","created":"2024-10-27","cited_by_count":63,"area":"diffusion"},{"id":"2309.09968","title":"Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees","created":"2023-09-18","cited_by_count":62,"area":null},{"id":"2211.06550","title":"TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data","created":"2022-11-12","cited_by_count":57,"area":null},{"id":"2305.09696","title":"Generative Table Pre-training Empowers Models for Tabular Prediction","created":"2023-05-16","cited_by_count":55,"area":null},{"id":"2312.12112","title":"Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes","created":"2023-12-19","cited_by_count":52,"area":null},{"id":"2303.00918","title":"STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables","created":"2023-03-02","cited_by_count":49,"area":null},{"id":"2205.09435","title":"Adversarial random forests for density estimation and generative modeling","created":"2022-05-19","cited_by_count":44,"area":null},{"id":"2301.04819","title":"Data-centric AI: Perspectives and Challenges","created":"2023-01-12","cited_by_count":43,"area":null},{"id":"2310.12746","title":"TabuLa: Harnessing Language Models for Tabular Data Synthesis","created":"2023-10-19","cited_by_count":42,"area":"synth"},{"id":"2309.01472","title":"FinDiff: Diffusion Models for Financial Tabular Data Generation","created":"2023-09-04","cited_by_count":41,"area":"diffusion"},{"id":"2211.13358","title":"Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluation","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2405.09591","title":"A Comprehensive Survey on Data Augmentation","created":"2024-05-15","cited_by_count":40,"area":null},{"id":"2307.00467","title":"MissDiff: Training Diffusion Models on Tabular Data with Missing Values","created":"2023-07-02","cited_by_count":39,"area":"diffusion"},{"id":"2307.02106","title":"SoK: Privacy-Preserving Data Synthesis","created":"2023-07-05","cited_by_count":38,"area":null},{"id":"2312.06089","title":"TabMT: Generating tabular data with masked transformers","created":"2023-12-11","cited_by_count":36,"area":null},{"id":"2101.00598","title":"Copula Flows for Synthetic Data Generation","created":"2021-01-03","cited_by_count":35,"area":null},{"id":"2109.00666","title":"TabFairGAN: Fair Tabular Data Generation with Generative Adversarial Networks","created":"2021-09-02","cited_by_count":34,"area":null},{"id":"2310.16524","title":"Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data","created":"2023-10-25","cited_by_count":32,"area":null},{"id":"2206.08743","title":"Learning Fair Representation via Distributional Contrastive Disentanglement","created":"2022-06-17","cited_by_count":31,"area":null},{"id":"2209.08060","title":"PTab: Using the Pre-trained Language Model for Modeling Tabular Data","created":"2022-09-15","cited_by_count":30,"area":null},{"id":"2206.08555","title":"SOS: Score-based Oversampling for Tabular Data","created":"2022-06-17","cited_by_count":29,"area":"diffusion"},{"id":"2305.09235","title":"Synthetic data, real errors: how (not) to publish and use synthetic data","created":"2023-05-16","cited_by_count":29,"area":null},{"id":"2307.01610","title":"Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction","created":"2023-07-04","cited_by_count":29,"area":"safety"},{"id":"2402.04823","title":"How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data","created":"2024-02-07","cited_by_count":29,"area":null},{"id":"2101.10123","title":"Conditional Generative Models for Counterfactual Explanations","created":"2021-01-25","cited_by_count":28,"area":null},{"id":"2306.10308","title":"Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishing","created":"2023-06-17","cited_by_count":28,"area":null},{"id":"2405.17724","title":"ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models","created":"2024-05-28","cited_by_count":28,"area":"diffusion"},{"id":"2406.05216","title":"TabPFGen -- Tabular Data Generation with TabPFN","created":"2024-06-07","cited_by_count":28,"area":null},{"id":"2408.00483","title":"A Systematic Review on Long-Tailed Learning","created":"2024-08-01","cited_by_count":28,"area":null},{"id":"2504.16506","title":"A Comprehensive Survey of Synthetic Tabular Data Generation","created":"2025-04-23","cited_by_count":28,"area":"diffusion"},{"id":"2103.05844","title":"BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks","created":"2021-03-10","cited_by_count":27,"area":null},{"id":"2105.14969","title":"OCT-GAN: Neural ODE-based Conditional Tabular GANs","created":"2021-05-31","cited_by_count":27,"area":null},{"id":"2207.05295","title":"TabSynDex: A Universal Metric for Robust Evaluation of Synthetic Tabular Data","created":"2022-07-12","cited_by_count":27,"area":null},{"id":"2404.15821","title":"SynthEval: A Framework for Detailed Utility and Privacy Evaluation of Tabular Synthetic Data","created":"2024-04-24","cited_by_count":27,"area":null},{"id":"2304.02858","title":"A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation","created":"2023-04-06","cited_by_count":25,"area":null},{"id":"2202.03636","title":"Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesis","created":"2022-02-08","cited_by_count":24,"area":null},{"id":"2301.10053","title":"A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data","created":"2023-01-24","cited_by_count":24,"area":null},{"id":"2305.12081","title":"MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinement","created":"2023-05-20","cited_by_count":24,"area":null},{"id":"2310.15479","title":"AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing","created":"2023-10-24","cited_by_count":24,"area":"diffusion"},{"id":"2106.04590","title":"PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning","created":"2021-06-08","cited_by_count":23,"area":null},{"id":"2302.02913","title":"Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design","created":"2023-02-06","cited_by_count":23,"area":"diffusion"},{"id":"2305.11602","title":"Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing","created":"2023-05-19","cited_by_count":23,"area":null},{"id":"2310.16981","title":"Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark","created":"2023-10-25","cited_by_count":23,"area":null},{"id":"2210.13043","title":"Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data","created":"2022-10-24","cited_by_count":22,"area":null},{"id":"2211.01761","title":"PromptEHR: Conditional Electronic Healthcare Records Generation with Prompt Learning","created":"2022-10-11","cited_by_count":22,"area":null},{"id":"2307.04308","title":"Towards Cross-Table Masked Pretraining for Web Data Mining","created":"2023-07-10","cited_by_count":21,"area":null},{"id":"2207.09542","title":"Controllable Data Generation by Deep Learning: A Review","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2103.02071","title":"Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making","created":"2021-03-02","cited_by_count":19,"area":null},{"id":"2310.04429","title":"NetDiffus: Network Traffic Generation by Diffusion Models through Time-Series Imaging","created":"2023-09-23","cited_by_count":19,"area":"diffusion"},{"id":"2401.06883","title":"Scaling While Privacy Preserving: A Comprehensive Synthetic Tabular Data Generation and Evaluation in Learning Analytics","created":"2024-01-12","cited_by_count":19,"area":null},{"id":"2307.01701","title":"Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data","created":"2023-07-04","cited_by_count":18,"area":"safety"},{"id":"2402.06806","title":"Systematic Assessment of Tabular Data Synthesis","created":"2024-02-09","cited_by_count":18,"area":"synth"},{"id":"2410.12034","title":"A Survey on Deep Tabular Learning","created":"2024-10-15","cited_by_count":18,"area":null},{"id":"2502.18237","title":"Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints","created":"2025-02-25","cited_by_count":18,"area":null},{"id":"2109.14567","title":"Implicit Generative Copulas","created":"2021-09-29","cited_by_count":17,"area":null},{"id":"2302.12749","title":"SurvivalGAN: Generating Time-to-Event Data for Survival Analysis","created":"2023-02-24","cited_by_count":17,"area":null},{"id":"2312.10431","title":"Continuous Diffusion for Mixed-Type Tabular Data","created":"2023-12-16","cited_by_count":17,"area":"diffusion"},{"id":"2204.04797","title":"Multi-Label Clinical Time-Series Generation via Conditional GAN","created":"2022-04-10","cited_by_count":16,"area":null},{"id":"2312.05253","title":"DiSK: A Diffusion Model for Structured Knowledge","created":"2023-12-08","cited_by_count":16,"area":"diffusion"},{"id":"2406.01457","title":"Differentially Private Tabular Data Synthesis using Large Language Models","created":"2024-06-03","cited_by_count":16,"area":"synth"},{"id":"2408.02927","title":"HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection","created":"2024-08-06","cited_by_count":16,"area":"synth"},{"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":"2211.07588","title":"Row Conditional-TGAN for generating synthetic relational databases","created":"2022-11-14","cited_by_count":15,"area":null},{"id":"2407.02549","title":"Diffusion Models for Tabular Data Imputation and Synthetic Data Generation","created":"2024-07-02","cited_by_count":15,"area":"diffusion"},{"id":"2407.21523","title":"Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI","created":"2024-07-31","cited_by_count":15,"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":"2506.05940","title":"Exponential Family Variational Flow Matching for Tabular Data Generation","created":"2025-06-06","cited_by_count":15,"area":"diffusion"},{"id":"2106.08971","title":"Model-Based Counterfactual Synthesizer for Interpretation","created":"2021-06-16","cited_by_count":14,"area":null},{"id":"2211.05764","title":"DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systems","created":"2022-11-09","cited_by_count":14,"area":null},{"id":"2306.12806","title":"Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness","created":"2023-06-22","cited_by_count":14,"area":null},{"id":"2312.05114","title":"The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against \"Truly Anonymous\" Synthetic Datasets","created":"2023-12-08","cited_by_count":14,"area":null},{"id":"2404.12404","title":"EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models","created":"2024-04-15","cited_by_count":14,"area":"synth"},{"id":"2406.04619","title":"CTSyn: A Foundation Model for Cross Tabular Data Generation","created":"2024-06-07","cited_by_count":14,"area":"diffusion"},{"id":"2501.12012","title":"TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Data","created":"2025-01-21","cited_by_count":14,"area":null},{"id":"2307.03577","title":"CuTS: Customizable Tabular Synthetic Data Generation","created":"2023-07-07","cited_by_count":13,"area":null},{"id":"2307.10430","title":"DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation","created":"2023-07-19","cited_by_count":13,"area":null},{"id":"2404.08434","title":"An improved tabular data generator with VAE-GMM integration","created":"2024-04-12","cited_by_count":13,"area":null},{"id":"2406.13985","title":"The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging","created":"2024-06-20","cited_by_count":13,"area":null},{"id":"2104.10680","title":"Causal-TGAN: Generating Tabular Data Using Causal Generative Adversarial Networks","created":"2021-04-21","cited_by_count":12,"area":null},{"id":"2105.04144","title":"Transitioning from Real to Synthetic data: Quantifying the bias in model","created":"2021-05-10","cited_by_count":12,"area":null},{"id":"2207.14406","title":"Sequential Models in the Synthetic Data Vault","created":"2022-07-28","cited_by_count":12,"area":null},{"id":"2306.15636","title":"On the Usefulness of Synthetic Tabular Data Generation","created":"2023-06-27","cited_by_count":12,"area":null},{"id":"2404.08254","title":"Balanced Mixed-Type Tabular Data Synthesis with Diffusion Models","created":"2024-04-12","cited_by_count":12,"area":"diffusion"},{"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":"2506.00813","title":"TIME: TabPFN-Integrated Multimodal Engine for Robust Tabular-Image Learning","created":"2025-06-01","cited_by_count":12,"area":null},{"id":"2203.10794","title":"Human-Centric Artificial Intelligence Architecture for Industry 5.0 Applications","created":"2022-03-21","cited_by_count":11,"area":null},{"id":"2204.00144","title":"Effect of Balancing Data Using Synthetic Data on the Performance of Machine Learning Classifiers for Intrusion Detection in Computer Networks","created":"2022-04-01","cited_by_count":11,"area":null}],"next_cursor":"100"}