Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups

• URL: http://arxiv.org/abs/2110.13059v1
• Date: Mon, 25 Oct 2021 15:56:53 GMT
• Title: Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups
• Authors: David M. Knigge, David W. Romero, Erik J. Bekkers
• Abstract summary: Group convolutional neural networks (G-CNNs) have been shown to increase parameter efficiency and model accuracy. In this work, we investigate the properties of representations learned by regular G-CNNs, and show considerable parameter redundancy in group convolution kernels. We introduce convolution kernels that are separable over the subgroup and channel dimensions.
• Score: 14.029933823101084
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Group convolutional neural networks (G-CNNs) have been shown to increase parameter efficiency and model accuracy by incorporating geometric inductive biases. In this work, we investigate the properties of representations learned by regular G-CNNs, and show considerable parameter redundancy in group convolution kernels. This finding motivates further weight-tying by sharing convolution kernels over subgroups. To this end, we introduce convolution kernels that are separable over the subgroup and channel dimensions. In order to obtain equivariance to arbitrary affine Lie groups we provide a continuous parameterisation of separable convolution kernels. We evaluate our approach across several vision datasets, and show that our weight sharing leads to improved performance and computational efficiency. In many settings, separable G-CNNs outperform their non-separable counterpart, while only using a fraction of their training time. In addition, thanks to the increase in computational efficiency, we are able to implement G-CNNs equivariant to the $\mathrm{Sim(2)}$ group; the group of dilations, rotations and translations. $\mathrm{Sim(2)}$-equivariance further improves performance on all tasks considered.

Related papers

• Balanced Group Convolution: An Improved Group Convolution Based on Approximability Estimates [1.927926533063962]
  Group convolution effectively reduces the computational cost by grouping channels. We mathematically analyze the approximation of the group convolution to the standard convolution. We propose a novel variant of the group convolution called balanced group convolution, which shows a higher approximation with a small additional computational cost.
  arXiv  Detail & Related papers  (2023-10-19T04:39:38Z)
• Lie Group Decompositions for Equivariant Neural Networks [12.139222986297261]
  We show how convolution kernels can be parametrized to build models equivariant with respect to affine transformations. We evaluate the robustness and out-of-distribution generalisation capability of our model on the benchmark affine-invariant classification task.
  arXiv  Detail & Related papers  (2023-10-17T16:04:33Z)
• Neural Tangent Kernels Motivate Graph Neural Networks with Cross-Covariance Graphs [94.44374472696272]
  We investigate NTKs and alignment in the context of graph neural networks (GNNs) Our results establish the theoretical guarantees on the optimality of the alignment for a two-layer GNN. These guarantees are characterized by the graph shift operator being a function of the cross-covariance between the input and the output data.
  arXiv  Detail & Related papers  (2023-10-16T19:54:21Z)
• Scale-Rotation-Equivariant Lie Group Convolution Neural Networks (Lie Group-CNNs) [5.498285766353742]
  This study proposes a Lie group-CNN, which can keep scale-rotation-equivariance for image classification tasks. The Lie group-CNN can successfully extract geometric features and performs equivariant recognition on images with rotation and scale transformations.
  arXiv  Detail & Related papers  (2023-06-12T08:14:12Z)
• Deep Neural Networks with Efficient Guaranteed Invariances [77.99182201815763]
  We address the problem of improving the performance and in particular the sample complexity of deep neural networks. Group-equivariant convolutions are a popular approach to obtain equivariant representations. We propose a multi-stream architecture, where each stream is invariant to a different transformation.
  arXiv  Detail & Related papers  (2023-03-02T20:44:45Z)
• Learnable Commutative Monoids for Graph Neural Networks [0.0]
  Graph neural networks (GNNs) are highly sensitive to the choice of aggregation function. We show that GNNs equipped with recurrent aggregators are competitive with state-of-the-art permutation-invariant aggregators. We propose a framework for constructing learnable, commutative, associative binary operators.
  arXiv  Detail & Related papers  (2022-12-16T15:43:41Z)
• Group Equivariant Neural Architecture Search via Group Decomposition and Reinforcement Learning [17.291131923335918]
  We prove a new group-theoretic result in the context of equivariant neural networks. We also design an algorithm to construct equivariant networks that significantly improves computational complexity. We use deep Q-learning to search for group equivariant networks that maximize performance.
  arXiv  Detail & Related papers  (2021-04-10T19:37:25Z)
• LieTransformer: Equivariant self-attention for Lie Groups [49.9625160479096]
  Group equivariant neural networks are used as building blocks of group invariant neural networks. We extend the scope of the literature to self-attention, that is emerging as a prominent building block of deep learning models. We propose the LieTransformer, an architecture composed of LieSelfAttention layers that are equivariant to arbitrary Lie groups and their discrete subgroups.
  arXiv  Detail & Related papers  (2020-12-20T11:02:49Z)
• Towards Deeper Graph Neural Networks with Differentiable Group Normalization [61.20639338417576]
  Graph neural networks (GNNs) learn the representation of a node by aggregating its neighbors. Over-smoothing is one of the key issues which limit the performance of GNNs as the number of layers increases. We introduce two over-smoothing metrics and a novel technique, i.e., differentiable group normalization (DGN)
  arXiv  Detail & Related papers  (2020-06-12T07:18:02Z)
• Stochastic Flows and Geometric Optimization on the Orthogonal Group [52.50121190744979]
  We present a new class of geometrically-driven optimization algorithms on the orthogonal group $O(d)$. We show that our methods can be applied in various fields of machine learning including deep, convolutional and recurrent neural networks, reinforcement learning, flows and metric learning.
  arXiv  Detail & Related papers  (2020-03-30T15:37:50Z)
• Supervised Learning for Non-Sequential Data: A Canonical Polyadic Decomposition Approach [85.12934750565971]
  Efficient modelling of feature interactions underpins supervised learning for non-sequential tasks. To alleviate this issue, it has been proposed to implicitly represent the model parameters as a tensor. For enhanced expressiveness, we generalize the framework to allow feature mapping to arbitrarily high-dimensional feature vectors.
  arXiv  Detail & Related papers  (2020-01-27T22:38:40Z)

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.