arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.02514cs.LG
收藏

基于分数的随机微分方程生成图建模

Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院);AITRICS

Jaehyeong Jo, Seul Lee, Sung Ju Hwang

摘要:

生成图结构数据需要学习图的底层分布。然而,这是一个具有挑战性的问题,以前的图生成方法要么无法捕获图的置换不变性,要么无法充分建模节点和边缘之间的复杂依赖关系,这对于生成分子等真实世界的图至关重要。为了克服这些局限性,我们提出了一种新的基于得分的生成模型与连续时间框架的图。具体来说,我们提出了一个新的图形扩散过程,模型的节点和边缘的联合分布,通过一个系统的随机微分方程(SDES)。然后,我们推导出新的分数匹配目标,为建议的扩散过程中估计的联合对数密度相对于每个组件的梯度,并引入一个新的求解器的系统的SDES有效地从反向扩散过程中采样。我们在不同的数据集上验证了我们的图形生成方法,在这些数据集上,它可以实现比基线更优越或具有竞争力的性能。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规则的分子,证明了SDES系统在建模节点-边缘关系方面的有效性。我们的代码可在https://github.com/harryjo97/GDSS上获得。

英文摘要:

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.

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。

↑