https://scholars.lib.ntu.edu.tw/handle/123456789/626577
標題: | Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design | 作者: | Fan, Xiran CHUN HAO YANG Vemuri, Baba C. |
關鍵字: | Deep learning architectures and techniques | Statistical methods | 公開日期: | 1-六月-2022 | 卷: | 2022-June | 起(迄)頁: | 356 | 來源出版物: | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | 摘要: | Hyperbolic neural networks have been popular in the recent past due to their ability to represent hierarchical data sets effectively and efficiently. The challenge in developing these networks lies in the nonlinearity of the embedding space namely, the Hyperbolic space. Hyperbolic space is a homogeneous Riemannian manifold of the Lorentz group which is a semi-Riemannian manifold, i.e. a mani-fold equipped with an indefinite metric. Most existing methods (with some exceptions) use local linearization to define a variety of operations paralleling those used in traditional deep neural networks in Euclidean spaces. In this paper, we present a novel fully hyperbolic neural network which uses the concept of projections (embeddings) followed by an intrinsic aggregation and a nonlinearity all within the hyperbolic space. The novelty here lies in the projection which is designed to project data on to a lower-dimensional embedded hyperbolic space and hence leads to a nested hyperbolic space representation independently useful for dimensionality reduction. The main theoretical contribution is that the proposed embedding is proved to be isometric and equivariant under the Lorentz transformations, which are the natural isometric transformations in hyperbolic spaces. This projection is computationally efficient since it can be expressed by simple linear operations, and, due to the aforementioned equivariance property, it allows for weight sharing. The nested hyperbolic space representation is the core component of our network and therefore, we first compare this representation - independent of the network - with other dimensionality reduction methods such as tangent PCA, principal geodesic analysis (PGA) and HoroPCA. Based on this equivariant embedding, we develop a novel fully hyperbolic graph convolutional neural network architecture to learn the parameters of the projection. Finally, we present experiments demonstrating comparative performance of our network on several publicly available data sets. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/626577 | ISBN: | 9781665469463 | ISSN: | 10636919 | DOI: | 10.1109/CVPR52688.2022.00045 |
顯示於: | 應用數學科學研究所 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。