arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.07877cs.AI
收藏

R-GSN:一种基于拓扑结构的异构图相似网络

R-GSN: The Relation-based Graph Similar Network for Heterogeneous Graph

Xi'an Jiaotong University(西安交通大学)

Xinliang Wu, Mengying Jiang, Guizhong Liu

摘要:

异构图是现实生活中广泛存在的一种数据结构。目前,异构图上的图神经网络的研究越来越多。现有的异构图神经网络算法主要有两种思想,一种是基于元路径的,另一种则不是。基于元路径的思想往往需要大量的人工预处理,同时很难推广到大规模图。本文提出了一种通用的异构消息传递模式,设计了一种不需要元路径的R-GCN,与R-GCN相比有了很大的改进。实验表明,我们的R-GSN算法在ogbn-mag大规模异构图数据集上达到了最先进的性能。

英文摘要:

Heterogeneous graph is a kind of data structure widely existing in real life. Nowadays, the research of graph neural network on heterogeneous graph has become more and more popular. The existing heterogeneous graph neural network algorithms mainly have two ideas, one is based on meta-path and the other is not. The idea based on meta-path often requires a lot of manual preprocessing, at the same time it is difficult to extend to large scale graphs. In this paper, we proposed the general heterogeneous message passing paradigm and designed R-GSN that does not need meta-path, which is much improved compared to the baseline R-GCN. Experiments have shown that our R-GSN algorithm achieves the state-of-the-art performance on the ogbn-mag large scale heterogeneous graph dataset.

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。

↑