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 a-priori symmetries of the task and can manually construct an architecture with the corresponding equivariances. Our goal is a general approach for learning equivariances from data, without needing prior knowledge of a task's symmetries or custom task-specific architectures. We present a method for learning and encoding equivariances into networks by learning corresponding parameter sharing patterns from data. Our method can provably encode equivariance-inducing parameter sharing for any finite group of symmetry transformations, and we find experimentally that it can automatically learn a variety of equivariances from symmetries in data. We provide our experiment code and pre-trained models at https://github.com/AllanYangZhou/metalearning-symmetries.

这篇研究论文介绍了一种从数据学习平移对称性、提高深度学习在图像处理任务中的性能的方法，而非人为设计具有相应等变性质的架构，其通过学习相应的参数共享模式来实现对等变性的学习及编码，并且结果显示其成功替代了传统手动构建深度学习架构的方法。

通过重新参数化实现元学习对称性