Autoregressive Diffusion Model for Graph Generation-猫眼课题宝

DOI：

10.48550/arxiv.2307.08849

发表时间：

2023-07

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Lingkai Kong;Jiaming Cui;Haotian Sun;Yuchen Zhuang;B. Prakash;Chao Zhang

基于扩散的图形生成模型最近取得了可喜的成果，图形生成。然而，现有的基于扩散的图生成模型大多是在去量化的邻接矩阵空间中应用高斯扩散的一次性生成模型。这样的策略可能遭受模型训练困难、采样速度慢以及不能结合约束的问题。我们提出了一个自回归扩散模型的图形生成。与现有的方法不同，我们定义了一个节点吸收扩散过程，直接在离散图空间。对于前向扩散，我们设计了一个扩散排序网络，它从图拓扑中学习一个数据依赖的节点吸收排序。对于反向生成，我们设计了一个\ldblquote去噪网络}，它使用反向节点排序，通过预测新节点的节点类型及其与先前去噪节点的边来有效地重建图。基于图的排列不变性，我们证明了两个网络可以通过优化一个简单的数据似然下界来联合训练。我们在六个不同的通用图数据集和两个分子数据集上的实验表明，我们的模型实现了更好的或与以前的最先进的生成性能相当，同时具有快速的生成速度。

Diffusion-based graph generative models have recently obtained promising results for graph generation. However, existing diffusion-based graph generative models are mostly one-shot generative models that apply Gaussian diffusion in the dequantized adjacency matrix space. Such a strategy can suffer from difficulty in model training, slow sampling speed, and incapability of incorporating constraints. We propose an \emph{autoregressive diffusion} model for graph generation. Unlike existing methods, we define a node-absorbing diffusion process that operates directly in the discrete graph space. For forward diffusion, we design a \emph{diffusion ordering network}, which learns a data-dependent node absorbing ordering from graph topology. For reverse generation, we design a \emph{denoising network} that uses the reverse node ordering to efficiently reconstruct the graph by predicting the node type of the new node and its edges with previously denoised nodes at a time. Based on the permutation invariance of graph, we show that the two networks can be jointly trained by optimizing a simple lower bound of data likelihood. Our experiments on six diverse generic graph datasets and two molecule datasets show that our model achieves better or comparable generation performance with previous state-of-the-art, and meanwhile enjoys fast generation speed.

Autoregressive Diffusion Model for Graph Generation

文献摘要

相似文献