arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.15437cs.LGcs.SIstat.ML
收藏

GPT-GNN:图神经网络的生成式预训练

GPT-GNN: Generative Pre-Training of Graph Neural Networks

University of California, Los Angeles(加利福尼亚大学洛杉矶分校);Microsoft Research(微软研究院)

Ziniu Hu, Yuxiao Dong, Kuansan Wang, Kai-Wei Chang, Yizhou Sun

摘要:

图神经网络(GNN)已被证明是强大的建模图结构的数据。然而,训练GNN通常需要大量特定于任务的标记数据,而获得这些数据通常非常昂贵。减少标记工作的一种有效方法是在具有自我监督的未标记数据上预训练表达性GNN模型,然后将学习到的模型转移到只有几个标签的下游任务。在本文中,我们提出了GPT-GNN框架,通过生成预训练来初始化GNN。GPT-GNN引入了一个自监督的属性图生成任务来预训练GNN,以便它可以捕获图的结构和语义属性。我们将图生成的可能性分解为两个部分:1)属性生成和2)边生成。通过对这两个组件进行建模,GPT-GNN在生成过程中捕获了节点属性和图结构之间的固有依赖关系。在十亿规模的开放学术图谱和亚马逊推荐数据上进行的综合实验表明,GPT-GNN在各种下游任务中的性能明显优于没有预训练的最先进的GNN模型,最高可达9.1%。

英文摘要:

Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data. However, training GNNs usually requires abundant task-specific labeled data, which is often arduously expensive to obtain. One effective way to reduce the labeling effort is to pre-train an expressive GNN model on unlabeled data with self-supervision and then transfer the learned model to downstream tasks with only a few labels. In this paper, we present the GPT-GNN framework to initialize GNNs by generative pre-training. GPT-GNN introduces a self-supervised attributed graph generation task to pre-train a GNN so that it can capture the structural and semantic properties of the graph. We factorize the likelihood of the graph generation into two components: 1) Attribute Generation and 2) Edge Generation. By modeling both components, GPT-GNN captures the inherent dependency between node attributes and graph structure during the generative process. Comprehensive experiments on the billion-scale Open Academic Graph and Amazon recommendation data demonstrate that GPT-GNN significantly outperforms state-of-the-art GNN models without pre-training by up to 9.1% across various downstream tasks.

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。

↑