Group Equivariant Conditional Neural Processes

Abstract

We present the group equivariant conditional neural process (EquivCNP), a meta-learning method with permutation invariance in a data set as in conventional conditional neural processes (CNPs), and it also has transformation equivariance in data space. Incorporating group equivariance, such as rotation and scaling equivariance, provides a way to consider the symmetry of real-world data. We give a decomposition theorem for permutation-invariant and group-equivariant maps, which leads us to construct EquivCNPs with an infinite-dimensional latent space to handle group symmetries. In this paper, we build architecture using Lie group convolutional layers for practical implementation. We show that EquivCNP with translation equivariance achieves comparable performance to conventional CNPs in a 1D regression task. Moreover, we demonstrate that incorporating an appropriate Lie group equivariance, EquivCNP is capable of zero-shot generalization for an image-completion task by selecting an appropriate Lie group equivariance.

References in corpus (12)

• Auto-Encoding Variational Bayes
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Group Equivariant Convolutional Networks
• On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
• Depthwise Separable Convolutions for Neural Machine Translation
• General $E(2)$-Equivariant Steerable CNNs
• Hamiltonian Graph Networks with ODE Integrators
• Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
• DeepSphere: towards an equivariant graph-based spherical CNN
• Learning Group Structure and Disentangled Representations of Dynamical Environments
• Meta-Learning surrogate models for sequential decision making