论文标题
通过重新聚体的元学习对称性
Meta-Learning Symmetries by Reparameterization
论文作者
论文摘要
许多成功的深度学习体系结构都与某些转换相等，以节省参数并改善概括：最著名的是，卷积层与输入的变化一样。这种方法只有在从业人员知道任务的对称性并可以手动构建具有相应的等效性的建筑时才起作用。我们的目标是一种从数据中学习均值的方法，而无需设计自定义特定任务的体系结构。我们提出了一种通过从数据中学习相应的参数共享模式来学习和编码等效化的方法。我们的方法可以证明代表任何有限的对称转换组的诱导诱导参数共享。我们的实验表明，它可以自动学习编码对图像处理任务中使用的常见转换的等效性。我们在https://github.com/allanyangzhou/metalearning-symeties上提供实验代码。
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. Our method can provably represent equivariance-inducing parameter sharing for any finite group of symmetry transformations. Our experiments suggest that it can automatically learn to encode equivariances to common transformations used in image processing tasks. We provide our experiment code at https://github.com/AllanYangZhou/metalearning-symmetries.
