对称性的逆学习
Inverse Learning of Symmetries
摘要：
对称变换诱导不变性，这经常用深层潜变量模型来描述。在许多复杂的领域，如化学空间，可以观察到不变性，但相应的对称变换不能用解析公式表示。我们建议使用由两个潜在子空间组成的模型来学习对称变换，其中第一个子空间捕获目标，第二子空间捕获剩余的不变信息。我们的方法是基于深信息瓶颈与连续互信息正则化相结合。与以前的方法不同，我们专注于最小化连续域中的互信息的挑战性任务。为此，我们将互信息的计算建立在相关矩阵上，并结合双射变量变换。大量的实验表明，我们的模型在人工和分子数据集上的性能优于最先进的方法。
英文摘要：
Symmetry transformations induce invariances which are frequently described with deep latent variable models. In many complex domains, such as the chemical space, invariances can be observed, yet the corresponding symmetry transformation cannot be formulated analytically. We propose to learn the symmetry transformation with a model consisting of two latent subspaces, where the first subspace captures the target and the second subspace the remaining invariant information. Our approach is based on the deep information bottleneck in combination with a continuous mutual information regulariser. Unlike previous methods, we focus on the challenging task of minimising mutual information in continuous domains. To this end, we base the calculation of mutual information on correlation matrices in combination with a bijective variable transformation. Extensive experiments demonstrate that our model outperforms state-of-the-art methods on artificial and molecular datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
