We view disentanglement learning as discovering an underlying structure that equivariantly reflects the factorized variations shown in data. Traditionally, such a structure is fixed to be a vector space with data variations represented by translations along individual latent dimensions. We argue this simple structure is suboptimal since it requires the model to learn to discard the properties (e.g. different scales of changes, different levels of abstractness) of data variations, which is an extra work than equivariance learning. Instead, we propose to encode the data variations with groups, a structure not only can equivariantly represent variations, but can also be adaptively optimized to preserve the properties of data variations. Considering it is hard to conduct training on group structures, we focus on Lie groups and adopt a parameterization using Lie algebra. Based on the parameterization, some disentanglement learning constraints are naturally derived. A simple model named Commutative Lie Group VAE is introduced to realize the group-based disentanglement learning. Experiments show that our model can effectively learn disentangled representations without supervision, and can achieve state-of-the-art performance without extra constraints.
翻译:我们把分解学习视为发现一个基本结构,这种结构会以等同方式反映数据显示的因子变量。 传统上, 这种结构被固定为矢量空间, 其数据变量以单个潜伏维度的翻译为代表。 我们认为这种简单结构不理想, 因为它要求模型学会丢弃数据变量的属性( 例如不同的变化规模、 不同程度的抽象性), 这比等异性学习是一种额外的工作。 相反, 我们提议将数据变量与组进行编码, 这种结构不仅可以等同地代表变异,而且可以适应性地优化以保存数据变量的特性。 考虑到在组结构上进行培训是困难的, 我们侧重于利伊组, 并采用利叶代数参数化的参数化。 基于参数化, 某些分解学习限制是自然产生的。 一个名为“ 异异性类组 VAE” 的简单模型被引入, 以实现以集团为基础的分解学习。 实验表明, 我们的模型可以在没有监督的情况下有效地学习相交的表达, 并且可以在没有额外限制的情况下实现状态性性能。