arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.05809cs.LG
收藏

简单图卷积网络

Simple Graph Convolutional Networks

University of Padua(帕多瓦大学)

Luca Pasa, Nicolò Navarin, Wolfgang Erb, Alessandro Sperduti

摘要:

许多用于图的神经网络都是基于十多年前提出的图卷积算子。从那时起,已经提出了许多替代定义,这些定义往往会增加模型的复杂性(和非线性)。在本文中,我们遵循相反的方向,提出了简单的图卷积算子,可以在单层图卷积网络中实现。我们表明,我们的卷积算子比文献中的许多建议更有理论基础,并且在所考虑的基准数据集上表现出最先进的预测性能。

英文摘要:

Many neural networks for graphs are based on the graph convolution operator, proposed more than a decade ago. Since then, many alternative definitions have been proposed, that tend to add complexity (and non-linearity) to the model. In this paper, we follow the opposite direction by proposing simple graph convolution operators, that can be implemented in single-layer graph convolutional networks. We show that our convolution operators are more theoretically grounded than many proposals in literature, and exhibit state-of-the-art predictive performance on the considered benchmark datasets.

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。

↑