论文标题
图形的扩散模型受益于离散状态空间
Diffusion Models for Graphs Benefit From Discrete State Spaces
论文作者
论文摘要
证明对生成任务非常有力，将扩散概率模型和得分匹配模型非常强大。尽管这些方法也已应用于离散图的生成，但到目前为止，它们依赖于连续的高斯扰动。相反，在这项工作中，我们建议使用离散的噪声进行向前的马尔可夫进程。这样可以确保在每个中间步骤中该图保持离散。与以前的方法相比，我们在四个数据集和多个架构上的实验结果表明，使用离散的no缩过程会导致产生的较高质量样品，指示平均MMD降低1.5倍。此外，降级步骤的数量从1000步减少到32个步骤，从而导致更快的采样步骤。
Denoising diffusion probabilistic models and score-matching models have proven to be very powerful for generative tasks. While these approaches have also been applied to the generation of discrete graphs, they have, so far, relied on continuous Gaussian perturbations. Instead, in this work, we suggest using discrete noise for the forward Markov process. This ensures that in every intermediate step the graph remains discrete. Compared to the previous approach, our experimental results on four datasets and multiple architectures show that using a discrete noising process results in higher quality generated samples indicated with an average MMDs reduced by a factor of 1.5. Furthermore, the number of denoising steps is reduced from 1000 to 32 steps, leading to a 30 times faster sampling procedure.
