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.
Improving Graph Few-shot Learning with Hyperbolic Space and Denoising Diffusion
Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, College of Computer Science and Technology, Jilin University(教育部符号计算与知识工程重点实验室,计算机科学与技术学院,吉林大学);School of Mathematical and Computer Sciences, Heriot-Watt University(数学与计算机科学学院,赫瑞-沃顿大学);Department of Information Engineering and Computer Science, University of Trento(信息工程与计算机科学系,特伦托大学)
Hyperbolic Graph Representation Learning for Differential Diagnosis on Biomedical Knowledge Graphs
Università degli Studi di Milano(米兰大学);Università della Svizzera italiana (USI)(瑞士意大利语大学);Politecnico di Milano(米兰理工大学);Aalto University(阿尔托大学);FGV(杰图利奥·瓦加斯基金会)
Enhancing Hyperbolic Graph Embeddings via Contrastive Learning
Harbin Institute of Technology(Shenzhen)(哈尔滨工业大学(深圳));The Chinese University of Hong Kong(香港中文大学);Huawei Technologies co.ltd(华为技术有限公司);Shenzhen University(深圳大学)
Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs
Beijing University of Posts and Telecommunications(北京邮电大学);Florida State University(佛罗里达州立大学);Beihang University(北京航空航天大学);University of Illinois at Chicago(伊利诺伊大学芝加哥分校)