arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.07618cs.LGcs.AIq-bio.QM
收藏

双曲图扩散模型

Hyperbolic Graph Diffusion Model

East China Normal University(华东师范大学);Information Engineering University(信息工程大学)

Lingfeng Wen, Xuan Tang, Mingjie Ouyang, Xiangxiang Shen, Jian Yang, Daxin Zhu, Mingsong Chen, Xian Wei

AI总结:

针对现实图数据的非欧几里得和层次特性,提出双曲图扩散模型(HGDM),利用双曲自编码器与潜在扩散模型提取层次分布并生成图,在高度层次结构的图生成质量上提升48%。

摘要:

扩散生成模型(DMs)在图像和图生成方面取得了有前景的结果。然而,现实世界中的图,如社交网络、分子图和交通图,通常具有非欧几里得拓扑和隐藏的层次结构。例如,图的度分布大多是幂律分布。当前的潜在扩散模型将层次数据嵌入到欧几里得空间中,这会导致失真并干扰分布的建模。相反,由于其指数增长特性,人们发现双曲空间更适合捕捉复杂的层次结构。为了同时利用扩散模型的数据生成能力和双曲嵌入提取潜在层次分布的能力,我们提出了一种新颖的图生成方法,称为双曲图扩散模型(HGDM),它由一个将节点编码为连续双曲嵌入的自编码器和一个在双曲潜在空间中运行的DM组成。HGDM通过构建一个包含边信息的双曲潜在节点空间来捕捉关键的图结构分布。大量实验表明,HGDM在通用图和分子生成基准中取得了更好的性能,在具有高度层次结构的图生成质量上提升了$48\%$。

英文摘要:

Diffusion generative models (DMs) have achieved promising results in image and graph generation. However, real-world graphs, such as social networks, molecular graphs, and traffic graphs, generally share non-Euclidean topologies and hidden hierarchies. For example, the degree distributions of graphs are mostly power-law distributions. The current latent diffusion model embeds the hierarchical data in a Euclidean space, which leads to distortions and interferes with modeling the distribution. Instead, hyperbolic space has been found to be more suitable for capturing complex hierarchical structures due to its exponential growth property. In order to simultaneously utilize the data generation capabilities of diffusion models and the ability of hyperbolic embeddings to extract latent hierarchical distributions, we propose a novel graph generation method called, Hyperbolic Graph Diffusion Model (HGDM), which consists of an auto-encoder to encode nodes into successive hyperbolic embeddings, and a DM that operates in the hyperbolic latent space. HGDM captures the crucial graph structure distributions by constructing a hyperbolic potential node space that incorporates edge information. Extensive experiments show that HGDM achieves better performance in generic graph and molecule generation benchmarks, with a $48\%$ improvement in the quality of graph generation with highly hierarchical structures.

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。

↑