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 1911.06253stat.MLcs.LG
收藏

理解具有广义几何散射变换的图神经网络

Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms

University of California, Los Angeles(加州大学洛杉矶分校);Université de Montréal(蒙特利尔大学);Mila – Quebec AI Institute(米拉-魁北克人工智能研究所);Columbia University(哥伦比亚大学);Michigan State University(密歇根州立大学)

Michael Perlmutter, Alexander Tong, Feng Gao, Guy Wolf, Matthew Hirn

AI总结:

本文基于通用非对称小波引入图的有窗和无窗几何散射变换,证明其具有与对称版本相同的理论保证,从而统一并扩展现有架构,为图神经网络提供可证明的稳定性和不变性。

摘要:

散射变换是一种基于小波的多层深度学习架构,可作为卷积神经网络的模型。最近,一些研究引入了散射变换在图等非欧几里得设置中的推广。我们的工作在这些构造的基础上,基于一类非常通用的非对称小波,引入了图的有窗和无窗几何散射变换。我们证明了这些非对称图散射变换具有与其对称对应物相同的许多理论保证。因此,所提出的构造统一并扩展了许多现有图散射架构的已知理论结果。在此过程中,通过引入一大类具有可证明的稳定性和不变性保证的网络,这项工作有助于弥合几何散射与其他图神经网络之间的差距。这些结果为未来处理图结构数据的深度学习架构奠定了基础,这些架构具有学习到的滤波器,并且可证明地具备理想的理论特性。

英文摘要:

The scattering transform is a multilayered wavelet-based deep learning architecture that acts as a model of convolutional neural networks. Recently, several works have introduced generalizations of the scattering transform for non-Euclidean settings such as graphs. Our work builds upon these constructions by introducing windowed and non-windowed geometric scattering transforms for graphs based upon a very general class of asymmetric wavelets. We show that these asymmetric graph scattering transforms have many of the same theoretical guarantees as their symmetric counterparts. As a result, the proposed construction unifies and extends known theoretical results for many of the existing graph scattering architectures. In doing so, this work helps bridge the gap between geometric scattering and other graph neural networks by introducing a large family of networks with provable stability and invariance guarantees. These results lay the groundwork for future deep learning architectures for graph-structured data that have learned filters and also provably have desirable theoretical properties.

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。

↑