paper-with-me

Papers

Cometh: A continuous-time discrete-state graph diffusion model

2024-06-10 · Antoine Siraudin, Fragkiskos D. Malliaros, Christopher Morris

Discrete-state denoising diffusion models led to state-of-the-art performance in graph generation, especially in the molecular domain. Recently, they have been transposed to continuous time, allowing more flexibility in the reverse process and a better trade-off between sampling efficiency and quality. Here, to leverage the benefits of both approaches, we propose Cometh, a continuous-time discrete-state graph diffusion model, tailored to the specificities of graph data. In addition, we also successfully replaced the set of structural encodings previously used in the discrete graph diffusion model with a single random-walk-based encoding, providing a simple and principled way to boost the model's expressive power. Empirically, we show that integrating continuous time leads to significant improvements across various metrics over state-of-the-art discrete-state diffusion models on a large set of molecular and non-molecular benchmark datasets. In terms of VUN samples, Cometh obtains a near-perfect performance of 99.5% on the planar graph dataset and outperforms DiGress by 12.6% on the large GuacaMol dataset.

📄 PDF Abstract BibTeX arXiv:2406.06449

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingGraph Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
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

COMETH: Convex Optimization for Multiview Estimation and Tracking of Humans

2025-08-28 · Enrico Martini, Ho Jin Choi, Nadia Figueroa, Nicola Bombieri arxiv

In the era of Industry 5.0, monitoring human activity is essential for ensuring both ergonomic safety and overall well-being. While multi-camera centralized setups improve pose estimation accuracy, they often suffer from…

Pose Estimation

Discrete-state Continuous-time Diffusion for Graph Generation

2024-05-19 · Zhe Xu, Ruizhong Qiu, Yuzhong Chen, Huiyuan Chen 외

Graph is a prevalent discrete data structure, whose generation has wide applications such as drug discovery and circuit design. Diffusion generative models, as an emerging research focus, have been applied to graph gener…

Drug DiscoveryGraph Generation

Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models

2025-12-24 · Geoffroy Morlat, Marceau Nahon, Augustin Chartouny, Raja Chatila 외 arxiv

Moral actions are judged not only by their outcomes but by the context in which they occur. We present COMETH (Contextual Organization of Moral Evaluation from Textual Human inputs), a framework that integrates a probabi…

Discrete-Continuous Smoothing and Mapping

2022-04-25 · Kevin J. Doherty, Ziqi Lu, Kurran Singh, John J. Leonard

We describe a general approach for maximum a posteriori (MAP) inference in a class of discrete-continuous factor graphs commonly encountered in robotics applications. While there are openly available tools providing flex…

Point Cloud Registration

Expectation Propagation for Continuous Time Bayesian Networks

2012-07-04 · Uri Nodelman, Daphne Koller, Christian R. Shelton

Continuous time Bayesian networks (CTBNs) describe structured stochastic processes with finitely many states that evolve over continuous time. A CTBN is a directed (possibly cyclic) dependency graph over a set of variabl…