arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.04560stat.MLcs.LG
收藏

在矩阵流形上构建神经网络:一种陀螺向量空间方法

Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach

CY Cergy Paris Université(CY塞尔吉-巴黎大学);ENSEA(国立高等电子及应用学院);CNRS(法国国家科学研究中心)

Xuan Son Nguyen, Shuo Yang

AI总结:

本文将陀螺向量空间概念推广至 SPD 与 Grassmann 矩阵流形,提出新型神经网络模型与层,并在动作识别和知识图谱补全任务中验证有效性。

摘要:

矩阵流形,例如对称正定(SPD)矩阵流形和 Grassmann 流形,出现在许多应用中。最近,通过应用陀螺群和陀螺向量空间理论——这是研究双曲几何的一个强大框架——一些工作尝试在矩阵流形上构建欧几里得神经网络的有原则的推广。然而,由于所考虑的流形在陀螺向量空间中缺少许多概念,例如内积和陀螺角,与为研究双曲几何而开发的技术和数学工具相比,这些工作提供的技术和数学工具仍然有限。在本文中,我们将陀螺向量空间中的一些概念推广到 SPD 和 Grassmann 流形,并提出用于在这些流形上构建神经网络的新模型和新层。我们在两个人应用中展示了我们方法的有效性,即人体动作识别和知识图谱补全。

英文摘要:

Matrix manifolds, such as manifolds of Symmetric Positive Definite (SPD) matrices and Grassmann manifolds, appear in many applications. Recently, by applying the theory of gyrogroups and gyrovector spaces that is a powerful framework for studying hyperbolic geometry, some works have attempted to build principled generalizations of Euclidean neural networks on matrix manifolds. However, due to the lack of many concepts in gyrovector spaces for the considered manifolds, e.g., the inner product and gyroangles, techniques and mathematical tools provided by these works are still limited compared to those developed for studying hyperbolic geometry. In this paper, we generalize some notions in gyrovector spaces for SPD and Grassmann manifolds, and propose new models and layers for building neural networks on these manifolds. We show the effectiveness of our approach in two applications, i.e., human action recognition and knowledge graph completion.

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。

↑