Author : Pavlo Melnyk
Publisher : Linköping University Electronic Press
ISBN 13 : 9180756808
Total Pages : 48 pages
Book Rating : 4.1/5 (87 download)
Book Synopsis Spherical NeurO(n)s for Geometric Deep Learning by : Pavlo Melnyk
Download or read book Spherical NeurO(n)s for Geometric Deep Learning written by Pavlo Melnyk and published by Linköping University Electronic Press. This book was released on 2024-09-03 with total page 48 pages. Available in PDF, EPUB and Kindle. Book excerpt: Felix Klein’s Erlangen Programme of 1872 introduced a methodology to unify non-Euclidean geometries. Similarly, geometric deep learning (GDL) constitutes a unifying framework for various neural network architectures. GDL is built from the first principles of geometry—symmetry and scale separation—and enables tractable learning in high dimensions. Symmetries play a vital role in preserving structural information of geometric data and allow models (i.e., neural networks) to adjust to different geometric transformations. In this context, spheres exhibit a maximal set of symmetries compared to other geometric entities in Euclidean space. The orthogonal group O(n) fully encapsulates the symmetry structure of an nD sphere, including both rotational and reflection symmetries. In this thesis, we focus on integrating these symmetries into a model as an inductive bias, which is a crucial requirement for addressing problems in 3D vision as well as in natural sciences and their related applications. In Paper A, we focus on 3D geometry and use the symmetries of spheres as geometric entities to construct neurons with spherical decision surfaces—spherical neurons—using a conformal embedding of Euclidean space. We also demonstrate that spherical neuron activations are non-linear due to the inherent non-linearity of the input embedding, and thus, do not necessarily require an activation function. In addition, we show graphically, theoretically, and experimentally that spherical neuron activations are isometries in Euclidean space, which is a prerequisite for the equivariance contributions of our subsequent work. In Paper B, we closely examine the isometry property of the spherical neurons in the context of equivariance under 3D rotations (i.e., SO(3)-equivariance). Focusing on 3D in this work and based on a minimal set of four spherical neurons (one learned spherical decision surface and three copies), the centers of which are rotated into the corresponding vertices of a regular tetrahedron, we construct a spherical filter bank. We call it a steerable 3D spherical neuron because, as we verify later, it constitutes a steerable filter. Finally, we derive a 3D steerability constraint for a spherical neuron (i.e., a single spherical decision surface). In Paper C, we present a learnable point-cloud descriptor invariant under 3D rotations and reflections, i.e., the O(3) actions, utilizing the steerable 3D spherical neurons we introduced previously, as well as vector neurons from related work. Specifically, we propose an embedding of the 3D steerable neurons into 4D vector neurons, which leverages end-to-end training of the model. The resulting model, termed TetraSphere, sets a new state-of-the-art performance classifying randomly rotated real-world object scans. Thus, our results reveal the practical value of steerable 3D spherical neurons for learning in 3D Euclidean space. In Paper D, we generalize to nD the concepts we previously established in 3D, and propose O(n)-equivariant neurons with spherical decision surfaces, which we call Deep Equivariant Hyper-spheres. We demonstrate how to combine them in a network that directly operates on the basis of the input points and propose an invariant operator based on the relation between two points and a sphere, which as we show, turns out to be a Gram matrix. In summary, this thesis introduces techniques based on spherical neurons that enhance the GDL framework, with a specific focus on equivariant and invariant learning on point sets.
