基于生成器的图生成 via 热扩散
Generator-based Graph Generation via Heat Diffusion
AI总结:
本文提出基于图拉普拉斯矩阵和热扩散的图生成框架,通过神经网络匹配生成器以生成新的图结构,有效捕捉真实和合成图的结构特性。
摘要:
图生成建模由于在化学、生物学、社交网络和知识表示中的广泛应用已成为一项关键任务。在本工作中,我们提出了一种新的框架,通过将生成器匹配(arXiv:2410.20587)范式适应到图结构数据上,来生成图。我们利用图拉普拉斯矩阵及其相关的热核来定义每个图上的连续时间扩散。拉普拉斯矩阵作为该扩散的无穷小生成器,其热核提供了一组初始图的条件扰动。神经网络被训练以匹配该生成器,通过最小化真实生成器与可学习替代器之间的Bregman散度。一旦训练完成,替代生成器被用来模拟反向扩散过程以采样新的图结构。我们的框架统一并泛化了现有的基于扩散的图生成模型,通过拉普拉斯注入领域特定的归纳偏差,同时保留神经近似器的灵活性。实验研究显示,我们的方法能够有效捕捉真实和合成图的结构特性。
英文摘要:
Graph generative modelling has become an essential task due to the wide range of applications in chemistry, biology, social networks, and knowledge representation. In this work, we propose a novel framework for generating graphs by adapting the Generator Matching (arXiv:2410.20587) paradigm to graph-structured data. We leverage the graph Laplacian and its associated heat kernel to define a continous-time diffusion on each graph. The Laplacian serves as the infinitesimal generator of this diffusion, and its heat kernel provides a family of conditional perturbations of the initial graph. A neural network is trained to match this generator by minimising a Bregman divergence between the true generator and a learnable surrogate. Once trained, the surrogate generator is used to simulate a time-reversed diffusion process to sample new graph structures. Our framework unifies and generalises existing diffusion-based graph generative models, injecting domain-specific inductive bias via the Laplacian, while retaining the flexibility of neural approximators. Experimental studies demonstrate that our approach captures structural properties of real and synthetic graphs effectively.
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。