Cometh: A continuous-time discrete-state graph diffusion model
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.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingGraph GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
COMETH: Convex Optimization for Multiview Estimation and Tracking of Humans
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 EstimationDiscrete-state Continuous-time Diffusion for Graph Generation
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 GenerationMorality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models
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
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 RegistrationExpectation Propagation for Continuous Time Bayesian Networks
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…