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 2008.09624cs.LGstat.ML
收藏

自然梯度下降的图神经网络优化

Optimization of Graph Neural Networks with Natural Gradient Descent

University of Notre Dame(圣母大学)

Mohammad Rasool Izadi, Yihao Fang, Robert Stevenson, Lizhen Lin

摘要:

在这项工作中,我们建议采用信息几何工具来优化图神经网络架构,如图卷积网络。更具体地说,我们开发了基于图的半监督学习的优化算法,通过在优化过程中采用自然梯度信息。这使我们能够有效地利用底层统计模型或参数空间的几何结构进行优化和推理。据我们所知,这是第一个利用自然梯度优化图神经网络的工作,可以扩展到其他半监督问题。高效的计算算法的开发和广泛的数值研究进行了证明我们的算法优于现有的算法,如ADAM和SGD的性能。

英文摘要:

In this work, we propose to employ information-geometric tools to optimize a graph neural network architecture such as the graph convolutional networks. More specifically, we develop optimization algorithms for the graph-based semi-supervised learning by employing the natural gradient information in the optimization process. This allows us to efficiently exploit the geometry of the underlying statistical model or parameter space for optimization and inference. To the best of our knowledge, this is the first work that has utilized the natural gradient for the optimization of graph neural networks that can be extended to other semi-supervised problems. Efficient computations algorithms are developed and extensive numerical studies are conducted to demonstrate the superior performance of our algorithms over existing algorithms such as ADAM and SGD.

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。

↑