论文标题
打破betatcvae中完全相关的咒语
Break The Spell Of Total Correlation In betaTCVAE
论文作者
论文摘要
在没有人工标签的情况下，数据中的独立和依赖性特征被混乱。如何构建模型的电感偏见以灵活分裂并有效地包含具有不同复杂性的特征，这是无监督的分解表示学习的主要焦点。本文提出了一种总相关性的新迭代分解路径，并从模型容量分配的角度解释了VAE的分离表示能力。新开发的目标函数将潜在的变量维度结合到联合分布中，同时减轻边缘分布组合的独立性约束，从而导致潜在变量具有更可操纵的先验分布。新型模型使VAE能够调整参数能力，以灵活地划分依赖性和独立的数据特征。各种数据集的实验结果显示模型容量与潜在变量分组大小（称为“ V”最佳ELBO轨迹）之间有一个有趣的相关性。此外，我们从经验上证明，所提出的方法通过合理的参数能力分配获得了更好的分解性能。
In the absence of artificial labels, the independent and dependent features in the data are cluttered. How to construct the inductive biases of the model to flexibly divide and effectively contain features with different complexity is the main focal point of unsupervised disentangled representation learning. This paper proposes a new iterative decomposition path of total correlation and explains the disentangled representation ability of VAE from the perspective of model capacity allocation. The newly developed objective function combines latent variable dimensions into joint distribution while relieving the independence constraints of marginal distributions in combination, leading to latent variables with a more manipulable prior distribution. The novel model enables VAE to adjust the parameter capacity to divide dependent and independent data features flexibly. Experimental results on various datasets show an interesting relevance between model capacity and the latent variable grouping size, called the "V"-shaped best ELBO trajectory. Additionally, we empirically demonstrate that the proposed method obtains better disentangling performance with reasonable parameter capacity allocation.
