arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.08773cs.LGcs.AIcs.SI
收藏

GraphRNN:使用深度自回归模型生成真实图

GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

Stanford University(斯坦福大学);University of Southern California(南加州大学)

Jiaxuan You, Rex Ying, Xiang Ren, William L. Hamilton, Jure Leskovec

摘要:

建模和生成图是研究生物学、工程学和社会科学中网络的基础。然而,由于图的非唯一、高维性质以及给定图中边之间存在的复杂、非局部依赖性,对图上的复杂分布进行建模然后从这些分布中有效地采样是具有挑战性的。在这里,我们提出了GraphRNN,这是一种深度自回归模型,可以解决上述挑战,并以最小的结构假设来近似任何图的分布。GraphRNN通过在一组有代表性的图上进行训练来学习生成图,并将图生成过程分解为一系列节点和边的形成,条件是到目前为止生成的图结构。为了定量评估GraphRNN的性能,我们引入了一套基准数据集,基线和基于最大平均离散度的新评估指标,这些指标可以测量各组图之间的距离。我们的实验表明,GraphRNN显著优于所有基线,学习生成与目标集的结构特征相匹配的各种图,同时还可以扩展到比以前的深度模型大50倍的图。

英文摘要:

Modeling and generating graphs is fundamental for studying networks in biology, engineering, and social sciences. However, modeling complex distributions over graphs and then efficiently sampling from these distributions is challenging due to the non-unique, high-dimensional nature of graphs and the complex, non-local dependencies that exist between edges in a given graph. Here we propose GraphRNN, a deep autoregressive model that addresses the above challenges and approximates any distribution of graphs with minimal assumptions about their structure. GraphRNN learns to generate graphs by training on a representative set of graphs and decomposes the graph generation process into a sequence of node and edge formations, conditioned on the graph structure generated so far. In order to quantitatively evaluate the performance of GraphRNN, we introduce a benchmark suite of datasets, baselines and novel evaluation metrics based on Maximum Mean Discrepancy, which measure distances between sets of graphs. Our experiments show that GraphRNN significantly outperforms all baselines, learning to generate diverse graphs that match the structural characteristics of a target set, while also scaling to graphs 50 times larger than previous deep models.

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。

↑