Log In Sign Up

Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints

by   Francesco Tonin, et al.

We introduce Constr-DRKM, a deep kernel method for the unsupervised learning of disentangled data representations. We propose augmenting the original deep restricted kernel machine formulation for kernel PCA by orthogonality constraints on the latent variables to promote disentanglement and to make it possible to carry out optimization without first defining a stabilized objective. After illustrating an end-to-end training procedure based on a quadratic penalty optimization algorithm with warm start, we quantitatively evaluate the proposed method's effectiveness in disentangled feature learning. We demonstrate on four benchmark datasets that this approach performs similarly overall to β-VAE on a number of disentanglement metrics when few training points are available, while being less sensitive to randomness and hyperparameter selection than β-VAE. We also present a deterministic initialization of Constr-DRKM's training algorithm that significantly improves the reproducibility of the results. Finally, we empirically evaluate and discuss the role of the number of layers in the proposed methodology, examining the influence of each principal component in every layer and showing that components in lower layers act as local feature detectors capturing the broad trends of the data distribution, while components in deeper layers use the representation learned by previous layers and more accurately reproduce higher-level features.


page 1

page 2

page 3

page 4


Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations

Recently there has been an increased interest in unsupervised learning o...

Linear Disentangled Representations and Unsupervised Action Estimation

Disentangled representation learning has seen a surge in interest over r...

Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representations

In this work we explore the generalization characteristics of unsupervis...

WeLa-VAE: Learning Alternative Disentangled Representations Using Weak Labels

Learning disentangled representations without supervision or inductive b...

Theory and Evaluation Metrics for Learning Disentangled Representations

We make two theoretical contributions to disentanglement learning by (a)...

Latent Space Exploration Using Generative Kernel PCA

Kernel PCA is a powerful feature extractor which recently has seen a ref...