Disentangling Learning Representations with Density Estimation
This addresses reliability problems in disentangled representations for applications in machine learning, but it appears incremental as it builds on existing methods with specific improvements.
The paper tackles the reliability issues in disentangled learning representations by introducing Gaussian Channel Autoencoder (GCAE), which uses flexible density estimation to achieve highly competitive and reliable disentanglement scores compared to state-of-the-art baselines.
Disentangled learning representations have promising utility in many applications, but they currently suffer from serious reliability issues. We present Gaussian Channel Autoencoder (GCAE), a method which achieves reliable disentanglement via flexible density estimation of the latent space. GCAE avoids the curse of dimensionality of density estimation by disentangling subsets of its latent space with the Dual Total Correlation (DTC) metric, thereby representing its high-dimensional latent joint distribution as a collection of many low-dimensional conditional distributions. In our experiments, GCAE achieves highly competitive and reliable disentanglement scores compared with state-of-the-art baselines.