paper-with-me

Papers

Discrete-state Continuous-time Diffusion for Graph Generation

2024-05-19 · Zhe Xu, Ruizhong Qiu, Yuzhong Chen, Huiyuan Chen, Xiran Fan, Menghai Pan, Zhichen Zeng, Mahashweta Das, Hanghang Tong

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 generation tasks. Overall, according to the space of states and time steps, diffusion generative models can be categorized into discrete-/continuous-state discrete-/continuous-time fashions. In this paper, we formulate the graph diffusion generation in a discrete-state continuous-time setting, which has never been studied in previous graph diffusion models. The rationale of such a formulation is to preserve the discrete nature of graph-structured data and meanwhile provide flexible sampling trade-offs between sample quality and efficiency. Analysis shows that our training objective is closely related to generation quality, and our proposed generation framework enjoys ideal invariant/equivariant properties concerning the permutation of node ordering. Our proposed model shows competitive empirical performance against state-of-the-art graph generation solutions on various benchmarks and, at the same time, can flexibly trade off the generation quality and efficiency in the sampling phase.

📄 PDF Abstract BibTeX arXiv:2405.11416

Code (1)

pricexu/disco 공식 구현 pytorch

Tasks

Drug DiscoveryGraph Generation

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

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 …

DenoisingGraph Generation

Convergence Analysis of Discrete Diffusion Model: Exact Implementation through Uniformization

2024-02-12 · Hongrui Chen, Lexing Ying

Diffusion models have achieved huge empirical success in data generation tasks. Recently, some efforts have been made to adapt the framework of diffusion models to discrete state space, providing a more natural approach …

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…

Denoising

Advancing Graph Generation through Beta Diffusion

2024-06-13 · Xinyang Liu, Yilin He, Bo Chen, Mingyuan Zhou

Diffusion models have excelled in generating natural images and are now being adapted to a variety of data types, including graphs. However, conventional models often rely on Gaussian or categorical diffusion processes, …

Graph Generation

Discrete Diffusion Schrödinger Bridge Matching for Graph Transformation

2024-10-02 · Jun Hyeong Kim, SeongHwan Kim, Seokhyun Moon, Hyeongwoo Kim 외

Transporting between arbitrary distributions is a fundamental goal in generative modeling. Recently proposed diffusion bridge models provide a potential solution, but they rely on a joint distribution that is difficult t…