We propose a family of First Hitting Diffusion Models (FHDM), deep generative models that generate data with a diffusion process that terminates at a random first hitting time. This yields an extension of the standard fixed-time diffusion models that terminate at a pre-specified deterministic time. Although standard diffusion models are designed for continuous unconstrained data, FHDM is naturally designed to learn distributions on continuous as well as a range of discrete and structure domains. Moreover, FHDM enables instance-dependent terminate time and accelerates the diffusion process to sample higher quality data with fewer diffusion steps. Technically, we train FHDM by maximum likelihood estimation on diffusion trajectories augmented from observed data with conditional first hitting processes (i.e., bridge) derived based on Doob's $h$-transform, deviating from the commonly used time-reversal mechanism. We apply FHDM to generate data in various domains such as point cloud (general continuous distribution), climate and geographical events on earth (continuous distribution on the sphere), unweighted graphs (distribution of binary matrices), and segmentation maps of 2D images (high-dimensional categorical distribution). We observe considerable improvement compared with the state-of-the-art approaches in both quality and speed.
Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matching
AIMS Research and Innovation Center（AIMS研究与创新中心）；Mila Québec AI Institute（魁北克AI研究所）；Université de Montréal（蒙特利尔大学）；SAIT Montreal AI Lab（蒙特利尔SAIT人工智能实验室）
Unsupervised and semi-supervised learning with Categorical Generative Adversarial Networks assisted by Wasserstein distance for dermoscopy image Classification
University of Saskatchewan（萨斯喀彻温大学）；Philips Canada（加拿大飞利浦）
TabSCM: A practical Framework for Generating Realistic Tabular Data
Federal Institute for Occupational Safety and Health (BAuA)（联邦职业安全与健康研究所）；School of Computation, Information and Technology, Technical University of Munich（计算、信息与技术学院，慕尼黑技术大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech
Huawei Noah's Ark Lab（华为诺亚实验室）；National Research University Higher School of Economics（俄罗斯国家研究大学高等经济学院）；National University of Science and Technology MISIS（俄罗斯科学与技术国立大学MISIS）
CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records
Department of Core Informatics, Graduate School of Informatics, Osaka Metropolitan University（核心信息学系，信息学研究生学校，大阪 Metropolitan 大学）；Smart Data & Knowledge Services Department, German Research Center for Artificial Intelligence (DFKI GmbH)（智能数据与知识服务部，德国人工智能研究中心（DFKI GmbH））；Department of Hematology and Department of Laboratory Medicine and Medical Informatics, Graduate School of Medicine, Osaka Metropolitan University（血液科和实验室医学与医学信息学系，医学研究生学校，大阪 Metropolitan 大学）
Classical Music Generation in Distinct Dastgahs with AlimNet ACGAN
University of Tabriz（大不里士大学）；Khajeh-Nasir University of Technology（哈杰·纳西尔理工大学）；Islamic Azad University, Sari branch（伊斯兰阿扎德大学萨里分校）；Islamic Azad University, Shiraz branch（伊斯兰阿扎德大学设拉子分校）
