arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.02591cs.LGcs.AIcs.SI
收藏

图上的生成式扩散模型:方法与应用

Generative Diffusion Models on Graphs: Methods and Applications

The Hong Kong Polytechnic University(香港理工大学);Michigan State University(密歇根州立大学)

Chengyi Liu, Wenqi Fan, Yunqing Liu, Jiatong Li, Hang Li, Hui Liu, Jiliang Tang, Qing Li

AI总结:

本文是图生成式扩散模型的综述,梳理SMLD、DDPM、SGM三类代表性算法,总结其在分子与蛋白质建模等领域的应用,探讨未来研究方向,并搭建了相关资源的GitHub项目网站。

摘要:

扩散模型作为一种新型生成范式,已在图像补全、图文翻译、视频生成等各类图像生成任务中取得显著成功。图生成是图领域的关键计算任务,具备众多实际应用,其目标是学习给定图的分布,进而生成新图。鉴于扩散模型在图像生成领域的巨大成功,近年来越来越多研究致力于利用这类技术推动图生成发展。本文首先对图上的生成式扩散模型进行全面综述,具体梳理了三类图扩散模型变体的代表性算法,即朗之万动力学分数匹配(Score Matching with Langevin Dynamics, SMLD)、去噪扩散概率模型(Denoising Diffusion Probabilistic Model, DDPM)以及基于分数的生成模型(Score-based Generative Model, SGM)。随后,本文总结了图上生成式扩散模型的主要应用,重点聚焦分子建模与蛋白质建模方向。最后,本文探讨了图结构数据上生成式扩散模型的潜在研究方向。针对本次综述,我们还搭建了一个GitHub项目网站,汇总了图上生成式扩散模型的相关支持资源,链接为:https://github.com/ChengyiLIU-cs/Generative-Diffusion-Models-on-Graphs

英文摘要:

Diffusion models, as a novel generative paradigm, have achieved remarkable success in various image generation tasks such as image inpainting, image-to-text translation, and video generation. Graph generation is a crucial computational task on graphs with numerous real-world applications. It aims to learn the distribution of given graphs and then generate new graphs. Given the great success of diffusion models in image generation, increasing efforts have been made to leverage these techniques to advance graph generation in recent years. In this paper, we first provide a comprehensive overview of generative diffusion models on graphs, In particular, we review representative algorithms for three variants of graph diffusion models, i.e., Score Matching with Langevin Dynamics (SMLD), Denoising Diffusion Probabilistic Model (DDPM), and Score-based Generative Model (SGM). Then, we summarize the major applications of generative diffusion models on graphs with a specific focus on molecule and protein modeling. Finally, we discuss promising directions in generative diffusion models on graph-structured data. For this survey, we also created a GitHub project website by collecting the supporting resources for generative diffusion models on graphs, at the link: https://github.com/ChengyiLIU-cs/Generative-Diffusion-Models-on-Graphs

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑