Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
In representation learning, there has been recent interest in developing algorithms to disentangle the ground-truth generative factors behind a dataset, and metrics to quantify how fully this occurs. However, these algorithms and metrics often assume that both representations and ground-truth factors are flat, continuous, and factorized, whereas many real-world generative processes involve rich hierarchical structure, mixtures of discrete and continuous variables with dependence between them, and even varying intrinsic dimensionality. In this work, we develop benchmarks, algorithms, and metrics for learning such hierarchical representations.
Code (1)
Tasks
DisentanglementRepresentation LearningSimilar Papers 제목 키워드 기반
Progressive Learning and Disentanglement of Hierarchical Representations
Learning rich representation from data is an important task for deep generative models such as variational auto-encoder (VAE). However, by extracting high-level abstractions in the bottom-up inference process, the goal o…
DisentanglementRepresentation LearningVariational Learning with Disentanglement-PyTorch
Unsupervised learning of disentangled representations is an open problem in machine learning. The Disentanglement-PyTorch library is developed to facilitate research, implementation, and testing of new variational algori…
DisentanglementSchedulingVariational Learning with Disentanglement-PyTorch
Unsupervised learning of disentangled representations is an open problem in machine learning. The Disentanglement-PyTorch library is developed to facilitate research, implementation, and testing of new variational algori…
DisentanglementSchedulingHow to Not Measure Disentanglement
To evaluate disentangled representations several metrics have been proposed. However, theoretical guarantees for conventional metrics of disentanglement are missing. Moreover, conventional metrics do not have a consisten…
DisentanglementReinforcement LearningTransfer LearningZero-Shot LearningBoxhead: A Dataset for Learning Hierarchical Representations
Disentanglement is hypothesized to be beneficial towards a number of downstream tasks. However, a common assumption in learning disentangled representations is that the data generative factors are statistically independe…
Disentanglement