Meta-Learning Symmetries by Reparameterization

Understand

Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input.

• This approach only works when practitioners know the symmetries of the task and can manually construct an architecture with the corresponding equivariances.
• Our goal is an approach for learning equivariances from data, without needing to design custom task-specific architectures.
• We present a method for learning and encoding equivariances into networks by learning corresponding parameter sharing patterns from data.