Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture
- URL: http://arxiv.org/abs/2410.12025v2
- Date: Sun, 02 Mar 2025 12:20:56 GMT
- Title: Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture
- Authors: Sajad Movahedi, Antonio Orvieto, Seyed-Mohsen Moosavi-Dezfooli,
- Abstract summary: We show that the input space curvature of a neural network remains invariant.<n>We also present experimental results to observe the consequences of GIH.
- Score: 22.225213114532533
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this paper, we propose the $\textit{geometric invariance hypothesis (GIH)}$, which argues that the input space curvature of a neural network remains invariant under transformation in certain architecture-dependent directions during training. We investigate a simple, non-linear binary classification problem residing on a plane in a high dimensional space and observe that$\unicode{x2014}$unlike MPLs$\unicode{x2014}$ResNets fail to generalize depending on the orientation of the plane. Motivated by this example, we define a neural network's $\textbf{average geometry}$ and $\textbf{average geometry evolution}$ as compact $\textit{architecture-dependent}$ summaries of the model's input-output geometry and its evolution during training. By investigating the average geometry evolution at initialization, we discover that the geometry of a neural network evolves according to the data covariance projected onto its average geometry. This means that the geometry only changes in a subset of the input space when the average geometry is low-rank, such as in ResNets. This causes an architecture-dependent invariance property in the input space curvature, which we dub GIH. Finally, we present extensive experimental results to observe the consequences of GIH and how it relates to generalization in neural networks.
Related papers
- Deep Learning as Ricci Flow [38.27936710747996]
Deep neural networks (DNNs) are powerful tools for approximating the distribution of complex data.
We show that the transformations performed by DNNs during classification tasks have parallels to those expected under Hamilton's Ricci flow.
Our findings motivate the use of tools from differential and discrete geometry to the problem of explainability in deep learning.
arXiv Detail & Related papers (2024-04-22T15:12:47Z) - A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications [71.809127869349]
This paper formalizes geometric graph as the data structure, on top of which we provide a unified view of existing models from the geometric message passing perspective.
We also summarize the applications as well as the related datasets to facilitate later research for methodology development and experimental evaluation.
arXiv Detail & Related papers (2024-03-01T12:13:04Z) - A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems [87.30652640973317]
Recent advances in computational modelling of atomic systems represent them as geometric graphs with atoms embedded as nodes in 3D Euclidean space.
Geometric Graph Neural Networks have emerged as the preferred machine learning architecture powering applications ranging from protein structure prediction to molecular simulations and material generation.
This paper provides a comprehensive and self-contained overview of the field of Geometric GNNs for 3D atomic systems.
arXiv Detail & Related papers (2023-12-12T18:44:19Z) - Affine Invariance in Continuous-Domain Convolutional Neural Networks [5.095097384893417]
Group invariance helps neural networks in recognizing patterns and features under geometric transformations.
This research studies affine invariance on continuous-domain convolutional neural networks.
Our research could eventually extend the scope of geometrical transformations that usual deep-learning pipelines can handle.
arXiv Detail & Related papers (2023-11-13T14:17:57Z) - From Complexity to Clarity: Analytical Expressions of Deep Neural Network Weights via Clifford's Geometric Algebra and Convexity [54.01594785269913]
We show that optimal weights of deep ReLU neural networks are given by the wedge product of training samples when trained with standard regularized loss.
The training problem reduces to convex optimization over wedge product features, which encode the geometric structure of the training dataset.
arXiv Detail & Related papers (2023-09-28T15:19:30Z) - Towards General-Purpose Representation Learning of Polygonal Geometries [62.34832826705641]
We develop a general-purpose polygon encoding model, which can encode a polygonal geometry into an embedding space.
We conduct experiments on two tasks: 1) shape classification based on MNIST; 2) spatial relation prediction based on two new datasets - DBSR-46K and DBSR-cplx46K.
Our results show that NUFTspec and ResNet1D outperform multiple existing baselines with significant margins.
arXiv Detail & Related papers (2022-09-29T15:59:23Z) - Plane Geometry Diagram Parsing [29.921409628478152]
We propose a powerful diagram based on deep learning and graph reasoning.
A modified instance segmentation method is proposed to extract geometric primitives.
The graph neural network (GNN) is leveraged to realize relation parsing and primitive classification.
arXiv Detail & Related papers (2022-05-19T07:47:01Z) - Revisiting Transformation Invariant Geometric Deep Learning: Are Initial
Representations All You Need? [80.86819657126041]
We show that transformation-invariant and distance-preserving initial representations are sufficient to achieve transformation invariance.
Specifically, we realize transformation-invariant and distance-preserving initial point representations by modifying multi-dimensional scaling.
We prove that TinvNN can strictly guarantee transformation invariance, being general and flexible enough to be combined with the existing neural networks.
arXiv Detail & Related papers (2021-12-23T03:52:33Z) - A singular Riemannian geometry approach to Deep Neural Networks II.
Reconstruction of 1-D equivalence classes [78.120734120667]
We build the preimage of a point in the output manifold in the input space.
We focus for simplicity on the case of neural networks maps from n-dimensional real spaces to (n - 1)-dimensional real spaces.
arXiv Detail & Related papers (2021-12-17T11:47:45Z) - PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling [103.09504572409449]
We propose a novel deep neural network based method, called PUGeo-Net, to generate uniform dense point clouds.
Thanks to its geometry-centric nature, PUGeo-Net works well for both CAD models with sharp features and scanned models with rich geometric details.
arXiv Detail & Related papers (2020-02-24T14:13:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.