paper-with-me

Papers

Unified Discrete Diffusion for Categorical Data

2024-02-06 · Lingxiao Zhao, Xueying Ding, Lijun Yu, Leman Akoglu

Discrete diffusion models have seen a surge of attention with applications on naturally discrete data such as language and graphs. Although discrete-time discrete diffusion has been established for a while, only recently Campbell et al. (2022) introduced the first framework for continuous-time discrete diffusion. However, their training and sampling processes differ significantly from the discrete-time version, necessitating nontrivial approximations for tractability. In this paper, we first present a series of mathematical simplifications of the variational lower bound that enable more accurate and easy-to-optimize training for discrete diffusion. In addition, we derive a simple formulation for backward denoising that enables exact and accelerated sampling, and importantly, an elegant unification of discrete-time and continuous-time discrete diffusion. Thanks to simpler analytical formulations, both forward and now also backward probabilities can flexibly accommodate any noise distribution, including different noise distributions for multi-element objects. Experiments show that our proposed USD3 (for Unified Simplified Discrete Denoising Diffusion) outperform all SOTA baselines on established datasets. We open-source our unified code at https://github.com/LingxiaoShawn/USD3.

📄 PDF Abstract BibTeX arXiv:2402.03701

Code (2)

lingxiaoshawn/usd3 공식 구현 pytorch
lingxiaoshawn/pard pytorch

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

MissHDD: Hybrid Deterministic Diffusion for Hetrogeneous Incomplete Data Imputation

2025-11-18 · Youran Zhou, Mohamed Reda Bouadjenek, Sunil Aryal arxiv

Incomplete data are common in real-world tabular applications, where numerical, categorical, and discrete attributes coexist within a single dataset. This heterogeneous structure presents significant challenges for exist…

Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction

2025-12-04 · Vincent Pauline, Tobias Höppe, Kirill Neklyudov, Alexander Tong 외 arxiv

Although diffusion models now occupy a central place in generative modeling, introductory treatments commonly assume Euclidean data and seldom clarify their connection to discrete-state analogues. This article is a self-…

Gaussian Processes

TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion

2026-02-26 · Donghong Cai, Jiarui Feng, Yanbo Wang, Da Zheng 외 arxiv

Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy. However, real-world tabular datasets increasingly contain free-form text fiel…

Tabular Data GenerationData Augmentation

Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data

2023-01-02 · Jumin Lee, Woobin Im, Sebin Lee, Sung-Eui Yoon

In this paper, we learn a diffusion model to generate 3D data on a scene-scale. Specifically, our model crafts a 3D scene consisting of multiple objects, while recent diffusion research has focused on a single object. To…

Simplex Relaxation for Discrete Diffusion

2026-08-11 · Jinya Sakurai, Patrick Pynadath, Satoshi Hayakawa, Jaehong Yoon 외 hf

Discrete diffusion models for categorical generation are defined by a corruption kernel, which determines the intermediate state space and the associated reverse prediction problem. We study uniform discrete diffusion an…