A Causal Ordering Prior for Unsupervised Representation Learning
Not on the map. Why?
Abstract (arXiv)
Unsupervised representation learning with variational inference relies heavily on independence assumptions over latent variables. Causal representation learning (CRL), however, argues that factors of variation in a dataset are, in fact, causally related. Allowing latent variables to be correlated, as a consequence of causal relationships, is more realistic and generalisable. So far, provably identifiable methods rely on: auxiliary information, weak labels, and interventional or even counterfactual data. Inspired by causal discovery with functional causal models, we propose a fully unsupervised representation learning method that considers a data generation process with a latent additive noise model (ANM). We encourage the latent space to follow a causal ordering via loss function based on the Hessian of the latent distribution.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 11 Jul 2023.
Builds on
30 of 45 references.
References · 30
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
- 2018Disentangling by Factorisingcited by 614
- 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
- 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
- 2016Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICAcited by 270
- 2013Causal Discovery with Continuous Additive Noise Modelscited by 252
- 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
- 2016Variational Deep Embedding: An Unsupervised and Generative Approach to Clusteringcited by 219
- 2022Weakly supervised causal representation learningcited by 140
- 2022Interventional Causal Representation Learningcited by 140
18 more
- 2022CITRIS: Causal Identifiability from Temporal Intervened Sequencescited by 132
- 2016Composing graphical models with neural networks for structured representations and fast inferencecited by 113
- 2022Score matching enables causal discovery of nonlinear additive noise modelscited by 108
- 2020ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICAcited by 102
- 2020On Disentangled Representations Learned From Correlated Datacited by 94
- 2022Identifiability of deep generative models without auxiliary informationcited by 70
- 2020Weakly Supervised Disentangled Generative Causal Representation Learningcited by 67
- 2022Diffusion Models for Causal Discovery via Topological Orderingcited by 64
- 2021gCastle: A Python Toolbox for Causal Discoverycited by 60
- 2017Gradient Estimators for Implicit Modelscited by 58
- 2023Identifiability of latent-variable and structural-equation models: from linear to nonlinearcited by 58
- 2018Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learningcited by 56
- 2023Score-based Causal Representation Learning with Interventionscited by 49
- 2021Learning Disentangled Representations in the Imaging Domaincited by 46
- 2021Multi-Facet Clustering Variational Autoencoderscited by 28
- 2022Symmetry-Based Representations for Artificial and Biological General Intelligencecited by 26
- 2021I Don't Need u: Identifiable Non-Linear ICA Without Side Informationcited by 21
- 2022GLANCE: Global to Local Architecture-Neutral Concept-based Explanationscited by 4
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.