On Symmetries in Convolutional Weights

• URL: http://arxiv.org/abs/2503.19215v2
• Date: Tue, 22 Apr 2025 18:35:31 GMT
• Title: On Symmetries in Convolutional Weights
• Authors: Bilal Alsallakh, Timothy Wroge, Vivek Miglani, Narine Kokhlikyan,
• Abstract summary: Mean kernels in internal layers tend to be symmetric about their centers instead of favoring specific directions.<n>We show how symmetry correlates with desirable properties such as shift and flip consistency, and might constitute an inherent inductive bias in convolutional neural networks.
• Score: 5.0445750949847605
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We explore the symmetry of the mean k x k weight kernel in each layer of various convolutional neural networks. Unlike individual neurons, the mean kernels in internal layers tend to be symmetric about their centers instead of favoring specific directions. We investigate why this symmetry emerges in various datasets and models, and how it is impacted by certain architectural choices. We show how symmetry correlates with desirable properties such as shift and flip consistency, and might constitute an inherent inductive bias in convolutional neural networks.

Related papers

• Exceptional Points and Stability in Nonlinear Models of Population Dynamics having $\mathcal{PT}$ symmetry [49.1574468325115]
  We analyze models governed by the replicator equation of evolutionary game theory and related Lotka-Volterra systems of population dynamics. We study the emergence of exceptional points in two cases: (a) when the governing symmetry properties are tied to global properties of the models, and (b) when these symmetries emerge locally around stationary states.
  arXiv  Detail & Related papers  (2024-11-19T02:15:59Z)
• The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof [50.49582712378289]
  We investigate the impact of neural parameter symmetries by introducing new neural network architectures. We develop two methods, with some provable guarantees, of modifying standard neural networks to reduce parameter space symmetries. Our experiments reveal several interesting observations on the empirical impact of parameter symmetries.
  arXiv  Detail & Related papers  (2024-05-30T16:32:31Z)
• Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks [79.16635054977068]
  We present a new class of equivariant neural networks, dubbed Lattice-Equivariant Neural Networks (LENNs) Our approach develops within a recently introduced framework aimed at learning neural network-based surrogate models Lattice Boltzmann collision operators. Our work opens towards practical utilization of machine learning-augmented Lattice Boltzmann CFD in real-world simulations.
  arXiv  Detail & Related papers  (2024-05-22T17:23:15Z)
• Lie Point Symmetry and Physics Informed Networks [59.56218517113066]
  We propose a loss function that informs the network about Lie point symmetries in the same way that PINN models try to enforce the underlying PDE through a loss function. Our symmetry loss ensures that the infinitesimal generators of the Lie group conserve the PDE solutions. Empirical evaluations indicate that the inductive bias introduced by the Lie point symmetries of the PDEs greatly boosts the sample efficiency of PINNs.
  arXiv  Detail & Related papers  (2023-11-07T19:07:16Z)
• Symmetry Induces Structure and Constraint of Learning [0.0]
  We unveil the importance of the loss function symmetries in affecting, if not deciding, the learning behavior of machine learning models. Common instances of mirror symmetries in deep learning include rescaling, rotation, and permutation symmetry. We show that the theoretical framework can explain intriguing phenomena, such as the loss of plasticity and various collapse phenomena in neural networks.
  arXiv  Detail & Related papers  (2023-09-29T02:21:31Z)
• Interrelation of equivariant Gaussian processes and convolutional neural networks [77.34726150561087]
  Currently there exists rather promising new trend in machine leaning (ML) based on the relationship between neural networks (NN) and Gaussian processes (GP) In this work we establish a relationship between the many-channel limit for CNNs equivariant with respect to two-dimensional Euclidean group with vector-valued neuron activations and the corresponding independently introduced equivariant Gaussian processes (GP)
  arXiv  Detail & Related papers  (2022-09-17T17:02:35Z)
• On the Importance of Asymmetry for Siamese Representation Learning [53.86929387179092]
  Siamese networks are conceptually symmetric with two parallel encoders. We study the importance of asymmetry by explicitly distinguishing the two encoders within the network. We find the improvements from asymmetric designs generalize well to longer training schedules, multiple other frameworks and newer backbones.
  arXiv  Detail & Related papers  (2022-04-01T17:57:24Z)
• Approximately Equivariant Networks for Imperfectly Symmetric Dynamics [24.363954435050264]
  We find that our models can outperform both baselines with no symmetry bias and baselines with overly strict symmetry in both simulated turbulence domains and real-world multi-stream jet flow.
  arXiv  Detail & Related papers  (2022-01-28T07:31:28Z)
• Encoding Involutory Invariance in Neural Networks [1.6371837018687636]
  In certain situations, Neural Networks (NN) are trained upon data that obey underlying physical symmetries. In this work, we explore a special kind of symmetry where functions are invariant with respect to involutory linear/affine transformations up to parity. Numerical experiments indicate that the proposed models outperform baseline networks while respecting the imposed symmetry. An adaption of our technique to convolutional NN classification tasks for datasets with inherent horizontal/vertical reflection symmetry has also been proposed.
  arXiv  Detail & Related papers  (2021-06-07T16:07:15Z)
• Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlators [0.0]
  symmetries of network densities may be determined via dual computations of network correlation functions. We demonstrate that the amount of symmetry in the initial density affects the accuracy of networks trained on Fashion-MNIST.
  arXiv  Detail & Related papers  (2021-06-01T18:00:06Z)
• Finding Symmetry Breaking Order Parameters with Euclidean Neural Networks [2.735801286587347]
  We demonstrate that symmetry equivariant neural networks uphold Curie's principle and can be used to articulate many symmetry-relevant scientific questions into simple optimization problems. We prove these properties mathematically and demonstrate them numerically by training a Euclidean symmetry equivariant neural network to learn symmetry-breaking input to deform a square into a rectangle and to generate octahedra tilting patterns in perovskites.
  arXiv  Detail & Related papers  (2020-07-04T17:24:21Z)
• Understanding Graph Neural Networks with Generalized Geometric Scattering Transforms [67.88675386638043]
  The scattering transform is a multilayered wavelet-based deep learning architecture that acts as a model of convolutional neural networks. We introduce 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.
  arXiv  Detail & Related papers  (2019-11-14T17:23:06Z)

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.