We propose a framework to analyze how multivariate representations disentangle ground-truth generative factors. A quantitative analysis of disentanglement has been based on metrics designed to compare how one variable explains each generative factor. Current metrics, however, may fail to detect entanglement that involves more than two variables, e.g., representations that duplicate and rotate generative factors in high dimensional spaces. In this work, we establish a framework to analyze information sharing in a multivariate representation with Partial Information Decomposition and propose a new disentanglement metric. This framework enables us to understand disentanglement in terms of uniqueness, redundancy, and synergy. We develop an experimental protocol to assess how increasingly entangled representations are evaluated with each metric and confirm that the proposed metric correctly responds to entanglement. Through experiments on variational autoencoders, we find that models with similar disentanglement scores have a variety of characteristics in entanglement, for each of which a distinct strategy may be required to obtain a disentangled representation.
翻译:我们提出一个框架来分析多变量的表达方式如何分解地面真实的基因变异因素。对分解的定量分析是根据用来比较一个变量如何解释每个基因变异因素的量度分析的。但是,目前的衡量方式可能无法检测出涉及两个以上变量的纠结,例如,在高维空间重复和旋转基因变异因素的表示方式。在这项工作中,我们建立了一个框架来分析多变量的表述方式,其中含有部分信息分解的分解,并提出了新的分解指标。这个框架使我们能够了解独特性、冗余和协同作用的分解。我们开发了一个实验协议来评估如何用每个指标来评估日益纠结的表达方式,并证实拟议的衡量方式对纠结的正确反应。我们通过对变形自动变形器的实验发现,相趋异分数的模型在纠结中具有各种特性,因为每一种不同的战略都可能需要获得分解的表达方式。