Unsupervised Model Selection for Variational Disentangled Representation Learning
Disentangled representations have recently been shown to improve fairness, data efficiency and generalisation in simple supervised and reinforcement learning tasks. To extend the benefits of disentangled representations to more complex domains and practical applications, it is important to enable hyperparameter tuning and model selection of existing unsupervised approaches without requiring access to ground truth attribute labels, which are not available for most datasets. This paper addresses this problem by introducing a simple yet robust and reliable method for unsupervised disentangled model selection. Our approach, Unsupervised Disentanglement Ranking (UDR), leverages the recent theoretical results that explain why variational autoencoders disentangle (Rolinek et al, 2019), to quantify the quality of disentanglement by performing pairwise comparisons between trained model representations. We show that our approach performs comparably to the existing supervised alternatives across 5,400 models from six state of the art unsupervised disentangled representation learning model classes. Furthermore, we show that the ranking produced by our approach correlates well with the final task performance on two different domains.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeDisentanglementFairnessmodelModel SelectionReinforcement LearningRepresentation LearningSimilar Papers 제목 키워드 기반
Learning Disentangled Discrete Representations
Recent successes in image generation, model-based reinforcement learning, and text-to-image generation have demonstrated the empirical advantages of discrete latent representations, although the reasons behind their bene…
Image GenerationModel-based Reinforcement LearningModel SelectionText to Image Generation+1DAVA: Disentangling Adversarial Variational Autoencoder
The use of well-disentangled representations offers many advantages for downstream tasks, e.g. an increased sample efficiency, or better interpretability. However, the quality of disentangled interpretations is often hig…
DisentanglementIndependent Subspace Analysis for Unsupervised Learning of Disentangled Representations
Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the var…
DisentanglementVariational InferenceVariational Inference of Disentangled Latent Concepts from Unlabeled Observations
Disentangled representations, where the higher level data generative factors are reflected in disjoint latent dimensions, offer several benefits such as ease of deriving invariant representations, transferability to othe…
DisentanglementVariational InferenceDisentangled Representation Learning with Sequential Residual Variational Autoencoder
Recent advancements in unsupervised disentangled representation learning focus on extending the variational autoencoder (VAE) with an augmented objective function to balance the trade-off between disentanglement and reco…
DecoderDisentanglementRepresentation Learning