mlsanityData to 7 Oct 2026

Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement

arXiv 2102.05185 ↗First posted 9 Feb 2021cs.LG cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 31 of its 56 references that are in the map. First posted on arXiv 9 Feb 2021.

Builds on

31 of 56 references.

References · 31

  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  3. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  4. 2020Object-Centric Learning with Slot Attentioncited by 865
  5. 2018Which Training Methods for GANs do actually Converge?cited by 672
  6. 2018Disentangling by Factorisingcited by 614
  7. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  8. 2016Ladder Variational Autoencoderscited by 315
  9. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
  10. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  11. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  12. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
19 more
  1. 2020Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Codingcited by 121
  2. 2017Learning Independent Causal Mechanismscited by 104
  3. 2017Building machines that adapt and compute like brainscited by 99
  4. 2020Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)cited by 91
  5. 2016Disentangling factors of variation in deep representations using adversarial trainingcited by 87
  6. 2013Deep Learning of Representations: Looking Forwardcited by 84
  7. 2018Learning Disentangled Joint Continuous and Discrete Representationscited by 83
  8. 2017Learning Disentangled Representations with Semi-Supervised Deep Generative Modelscited by 72
  9. 2018Structured Disentangled Representationscited by 62
  10. 2018FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discoverycited by 58
  11. 2020CausalVAE: Structured Causal Disentanglement in Variational Autoencodercited by 47
  12. 2016A Survey of Inductive Biases for Factorial Representation-Learningcited by 23
  13. 2019Learning Discrete and Continuous Factors of Data via Alternating Disentanglementcited by 23
  14. 2019Relevance Factor VAE: Learning and Identifying Disentangled Factorscited by 20
  15. 2021Evaluating the Interpretability of Generative Models by Interactive Reconstructioncited by 16
  16. 2019Disentangling Influence: Using Disentangled Representations to Audit Model Predictionscited by 11
  17. 2020Discond-VAE: Disentangling Continuous Factors from the Discretecited by 4
  18. 2017S-Isomap++: Multi Manifold Learning from Streaming Datacited by 2
  19. 2020Contagion Dynamics for Manifold Learningcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 3; 2023: 1; 2024: 3; 2025: 0; 2026: 2.

12 papers.

  1. 2022Disentangled Representation Learningcited by 111
  2. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  3. 2023Towards Robust Metrics for Concept Representation Evaluationcited by 29
  4. 2024Learning Discrete Concepts in Latent Hierarchical Modelscited by 17
  5. 2024Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Modelscited by 9
  6. 2021Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanationcited by 8
  7. 2024A Non-negative VAE:the Generalized Gamma Belief Networkcited by 4
  8. 2022Learning Unsupervised Hierarchies of Audio Conceptscited by 3
  9. 2021Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasetscited by 1
  10. 2021Boxhead: A Dataset for Learning Hierarchical Representationscited by 1
  11. 2026Enhancing Visual In-Context Learning by Multi-Faceted Fusioncited by 1
  12. 2026Counterfactual Explanations for Deep Two-Sample Testingcited by 0