Cover Image

Rethinking the Diffusion Models for Numerical Tabular Data Imputation from the Perspective of Wasserstein Gradient Flow

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Zhichao, Li, Haoxuan, Wang, Fangyikang, Zhang, Odin, Xu, Hu, Jiang, Xiaoyu, Song, Zhihuan, Wang, Eric H.
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Analyzing and Improving Diffusion Models for Time-Series Data Imputation: A Proximal Recursion Perspective
by: Chen, Zhichao, et al.
Published: (2026)

Rethinking the Flow-Based Gradual Domain Adaption: A Semi-Dual Optimal Transport Perspective
by: Chen, Zhichao, et al.
Published: (2026)

Towards Intrinsically Calibrated Uncertainty Quantification in Industrial Data-Driven Models via Diffusion Sampler
by: Ma, Yiran, et al.
Published: (2026)

Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
by: Villaizán-Vallelado, Mario, et al.
Published: (2024)

Neural Sinkhorn Gradient Flow
by: Zhu, Huminhao, et al.
Published: (2024)

Self-Supervision Improves Diffusion Models for Tabular Data Imputation
by: Liu, Yixin, et al.
Published: (2024)

DiffImpute: Tabular Data Imputation With Denoising Diffusion Probabilistic Model
by: Wen, Yizhu, et al.
Published: (2024)

stMCDI: Masked Conditional Diffusion Model with Graph Neural Network for Spatial Transcriptomics Data Imputation
by: Li, Xiaoyu, et al.
Published: (2024)

Dynamical Persistent Homology via Wasserstein Gradient Flow
by: Wang, Minghua, et al.
Published: (2024)

Missing Data Imputation by Reducing Mutual Information with Rectified Flows
by: Yu, Jiahao, et al.
Published: (2025)

MissDDIM: Deterministic and Efficient Conditional Diffusion for Tabular Data Imputation
by: Zhou, Youran, et al.
Published: (2025)

Learnable Prompt as Pseudo-Imputation: Rethinking the Necessity of Traditional EHR Data Imputation in Downstream Clinical Prediction
by: Liao, Weibin, et al.
Published: (2024)

Conditional Lagrangian Wasserstein Flow for Time Series Imputation
by: Qian, Weizhu, et al.
Published: (2024)

Analyzing and Mitigating Model Collapse in Rectified Flow Models
by: Zhu, Huminhao, et al.
Published: (2024)

Mitigating Hidden Confounding by Progressive Confounder Imputation via Large Language Models
by: Yang, Hao, et al.
Published: (2025)

Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
by: Bonet, Clément, et al.
Published: (2025)

Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees
by: Jolicoeur-Martineau, Alexia, et al.
Published: (2023)

A Closer Look on Memorization in Tabular Diffusion Model: A Data-Centric Perspective
by: Fang, Zhengyu, et al.
Published: (2025)

Rethinking Flow and Diffusion Bridge Models for Speech Enhancement
by: Wang, Dahan, et al.
Published: (2026)

CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation
by: Gorla, Aditya, et al.
Published: (2025)

On the Wasserstein Gradient Flow Interpretation of Drifting Models
by: Gretton, Arthur, et al.
Published: (2026)

Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow
by: Zheng, Bowen, et al.
Published: (2026)

Parameterized Wasserstein Gradient Flow
by: Jin, Yijie, et al.
Published: (2024)

Diffusion and Flow Matching Models for Tabular Data: A Survey
by: Li, Zhong, et al.
Published: (2025)

Understanding and Mitigating Memorization in Diffusion Models for Tabular Data
by: Fang, Zhengyu, et al.
Published: (2024)

Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective
by: Ye, Han-Jia, et al.
Published: (2023)

TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion
by: Cai, Donghong, et al.
Published: (2026)

Coupled Wasserstein Gradient Flows for Min-Max and Cooperative Games
by: Conger, Lauren, et al.
Published: (2024)

Forward Euler for Wasserstein Gradient Flows: Breakdown and Regularization
by: Xu, Yewei, et al.
Published: (2025)

Rethinking Distribution Shifts: Empirical Analysis and Inductive Modeling for Tabular Data
by: Wang, Tianyu, et al.
Published: (2023)

TabImpute: Universal Zero-Shot Imputation for Tabular Data
by: Feitelberg, Jacob, et al.
Published: (2025)

To Predict or Not To Predict? Proportionally Masked Autoencoders for Tabular Data Imputation
by: Kim, Jungkyu, et al.
Published: (2024)

A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows
by: Wang, Chenguang, et al.
Published: (2026)

Deep Generative Imputation Model for Missing Not At Random Data
by: Chen, Jialei, et al.
Published: (2023)

Inclusive KL Minimization: A Wasserstein-Fisher-Rao Gradient Flow Perspective
by: Zhu, Jia-Jie
Published: (2024)

Temporal Wasserstein Imputation: A Versatile Method for Time Series Imputation
by: Huang, Shuo-Chieh, et al.
Published: (2024)

Pruning for Sparse Diffusion Models based on Gradient Flow
by: Wan, Ben, et al.
Published: (2025)

Numerical Analysis on Neural Network Projected Schemes for Approximating One Dimensional Wasserstein Gradient Flows
by: Zuo, Xinzhe, et al.
Published: (2024)

When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
by: Lv, Xinpeng, et al.
Published: (2026)

Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
by: Chen, Yilan, et al.
Published: (2025)