Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
arXiv:2102.05185
Abstract
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.
arXiv commentICML 2021 paper, fixed incorrect version upload
References in corpus (17)
- Which Training Methods for GANs do actually Converge?
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- Disentangling by Factorising
- Towards Robust Interpretability with Self-Explaining Neural Networks
- Flexibly Fair Representation Learning by Disentanglement
- Structured Disentangled Representations
- Weakly-Supervised Disentanglement Without Compromises
- Learning Independent Causal Mechanisms
- Learning the Structure of Deep Sparse Graphical Models
- Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
- On Disentangled Representations Learned From Correlated Data
- A Survey of Inductive Biases for Factorial Representation-Learning
- Relevance Factor VAE: Learning and Identifying Disentangled Factors
- CausalVAE: Structured Causal Disentanglement in Variational Autoencoder
- S-Isomap++: Multi Manifold Learning from Streaming Data
- Disentangling Influence: Using Disentangled Representations to Audit Model Predictions
- Discond-VAE: Disentangling Continuous Factors from the Discrete