论文标题
通过随机微分方程系统的基于得分的生成建模
Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations
论文作者
论文摘要
生成图形结构化数据需要学习图形的基础分布。然而，这是一个具有挑战性的问题，先前的图生成方法要么无法捕获图形的置换式属性属性，要么无法充分对节点和边缘之间的复杂依赖性进行建模，这对于生成真实世界图至关重要。为了克服此类局限性，我们为具有连续时间框架的图表提出了一种基于分数的新型生成模型。具体而言，我们提出了一个新的图扩散过程，该过程通过随机微分方程（SDES）系统建模节点和边缘的联合分布。然后，我们得出了针对建议的扩散过程量身定制的新的分数匹配目标，以估算关节对数密度相对于每个组件的梯度，并为SDE系统引入一个新的求解器，以从反向扩散过程中有效采样。我们验证了不同数据集的图生成方法，在该数据集上，它要么在其上取得了比基线显着或竞争性能的。进一步的分析表明，我们的方法能够生成接近训练分布但不违反化学价值规则的分子，从而证明了SDE系统在建模节点边缘关系中的有效性。我们的代码可在https://github.com/harryjo97/gdss上找到。
Generating graph-structured data requires learning the underlying distribution of graphs. Yet, this is a challenging problem, and the previous graph generative methods either fail to capture the permutation-invariance property of graphs or cannot sufficiently model the complex dependency between nodes and edges, which is crucial for generating real-world graphs such as molecules. To overcome such limitations, we propose a novel score-based generative model for graphs with a continuous-time framework. Specifically, we propose a new graph diffusion process that models the joint distribution of the nodes and edges through a system of stochastic differential equations (SDEs). Then, we derive novel score matching objectives tailored for the proposed diffusion process to estimate the gradient of the joint log-density with respect to each component, and introduce a new solver for the system of SDEs to efficiently sample from the reverse diffusion process. We validate our graph generation method on diverse datasets, on which it either achieves significantly superior or competitive performance to the baselines. Further analysis shows that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule, demonstrating the effectiveness of the system of SDEs in modeling the node-edge relationships. Our code is available at https://github.com/harryjo97/GDSS.
