paper-with-me

Papers

Flow Matching for Tabular Data Synthesis

2025-11-30 · Bahrul Ilmi Nasution, Floor Eijkelboom, Mark Elliot, Richard Allmendinger, Christian A. Naesseth arxiv

Synthetic data generation is an important tool for privacy-preserving data sharing. Although diffusion models have set recent benchmarks, flow matching (FM) offers a promising alternative. This paper presents different ways to implement FM for tabular data synthesis. We provide a comprehensive empirical study that compares flow matching (FM and variational FM) with a state-of-the-art diffusion method (TabDDPM and TabSyn) in tabular data synthesis. We evaluate both the standard Optimal Transport (OT) and the Variance Preserving (VP) probability paths, and also compare deterministic and stochastic samplers -- something possible when learning to generate using \textit{variational} FM -- characterising the empirical relationship between data utility and privacy risk. Our key findings reveal that FM, particularly TabbyFlow, outperforms diffusion baselines. Flow matching methods also achieve better performance with remarkably low function evaluations ($\leq$ 100 steps), offering a substantial computational advantage. The choice of probability path is also crucial, as using the OT is a strong default and more robust to early stopping on average, while VP has potential to produce synthetic data with lower privacy risk. Lastly, our results show that making flows stochastic not only preserves marginal distributions but, in some instances, enables the generation of high utility synthetic data with reduced disclosure risk. The implementation code associated with this paper is publicly available at https://github.com/rulnasution/tabular-flow-matching.

📄 PDF Abstract BibTeX arXiv:2512.00698

Code (0)

등록된 구현이 없습니다.

Tasks

Synthetic Data Generation

Similar Papers 제목 키워드 기반

Understanding Latent Flow Models for Tabular Data Synthesis: Targets, Paths, and Sampling

2026-06-18 · Bahrul Ilmi Nasution arxiv

Synthetic tabular data enables microdata sharing in regulated domains, yet deploying continuous-time generative models requires balancing analytical utility, disclosure risk, and computational cost. Latent-space flow mod…

STaSy: Score-based Tabular data Synthesis

2022-10-08 · Jayoung Kim, Chaejeong Lee, Noseong Park

Tabular data synthesis is a long-standing research topic in machine learning. Many different methods have been proposed over the past decades, ranging from statistical methods to deep generative methods. However, it has …

DenoisingDiversity

Unsupervised Anomaly Detection Using Flow Matching on Tabular Data

2026-08-20 · Philip Konz, Tejaswini Medi, Margret Keuper arxiv

Financial anomaly detection often relies on large unlabeled transaction logs, where anomalous samples may already be present during training. Such training-set contamination violates the clean-normal data assumption unde…

Unsupervised Anomaly Detection

TSGM: Regular and Irregular Time-series Generation using Score-based Generative Models

2025-11-26 · Haksoo Lim, Jaehoon Lee, Sewon Park, Minjung Kim 외 arxiv

Score-based generative models (SGMs) have demonstrated unparalleled sampling quality and diversity in numerous fields, such as image generation, voice synthesis, and tabular data synthesis, etc. Inspired by those outstan…

Image Generation

BUFF: Boosted Decision Tree based Ultra-Fast Flow matching

2024-04-28 · Cheng Jiang, Sitian Qian, Huilin Qu

Tabular data stands out as one of the most frequently encountered types in high energy physics. Unlike commonly homogeneous data such as pixelated images, simulating high-dimensional tabular data and accurately capturing…