论文标题
带有张量产品表示的无监督分解
Unsupervised Disentanglement with Tensor Product Representations on the Torus
论文作者
论文摘要
使用自动编码器学习表示表示的当前方法几乎完全采用向量作为潜在表示。在这项工作中，我们建议为此目的采用张量产品结构。这样，所获得的表示自然会被删除。与针对正态分布特征的常规变体方法相反，我们表示中的潜在空间在一组单位圆上均匀分布。我们认为，潜在空间的圆环结构有效地捕获了生成因素。我们使用最近的工具来衡量无监督的分解，并在一系列实验中证明了我们方法在分离，完整性和信息性方面的优势。我们提出的方法的代码可在https://github.com/rotmanmi/unsupervise-disentanglement-torus上获得。
The current methods for learning representations with auto-encoders almost exclusively employ vectors as the latent representations. In this work, we propose to employ a tensor product structure for this purpose. This way, the obtained representations are naturally disentangled. In contrast to the conventional variations methods, which are targeted toward normally distributed features, the latent space in our representation is distributed uniformly over a set of unit circles. We argue that the torus structure of the latent space captures the generative factors effectively. We employ recent tools for measuring unsupervised disentanglement, and in an extensive set of experiments demonstrate the advantage of our method in terms of disentanglement, completeness, and informativeness. The code for our proposed method is available at https://github.com/rotmanmi/Unsupervised-Disentanglement-Torus.
