Data to 7 Oct 2026

On Disentangled Representations Learned From Correlated Data

arXiv 2006.07886 ↗First posted 14 Jun 2020cs.LG stat.MLcited by 94

Not on the map. Why?

Abstract (arXiv)

The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the gap to real-world scenarios by analyzing the behavior of the most prominent disentanglement approaches on correlated data in a large-scale empirical study (including 4260 models). We show and quantify that systematically induced correlations in the dataset are being learned and reflected in the latent representations, which has implications for downstream applications of disentanglement such as fairness. We also demonstrate how to resolve these latent correlations, either using weak supervision during training or by post-hoc correcting a pre-trained model with a small number of labels.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 24; 2023: 27; 2024: 17; 2025: 5; 2026: 9.

94 papers.

Sort:

By area:

2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
2022CITRIS: Causal Identifiability from Temporal Intervened Sequencescited by 132
2022Disentangled Representation Learningcited by 111
2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
2021Visual Representation Learning Does Not Generalize Strongly Within the Same Domaincited by 60
2023Causal Component Analysiscited by 56
2021Identifiable Deep Generative Models via Sparse Decodingcited by 54
2022Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systemscited by 50
2021Learning Disentangled Representations in the Imaging Domaincited by 46
2023Provably Learning Object-Centric Representationscited by 45
2022Disentanglement of Correlated Factors via Hausdorff Factorized Supportcited by 37
2023Subspace Identification for Multi-Source Domain Adaptationcited by 36

38 more

2022Identifying Weight-Variant Latent Causal Modelscited by 33
2022Invariant Causal Mechanisms through Distribution Matchingcited by 31
2023Conditional Mutual Information for Disentangled Representations in Reinforcement Learningcited by 27
2021Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANscited by 26
2022Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learningcited by 26
2021On Causally Disentangled Representationscited by 22
2023Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learningcited by 22
2024Learned feature representations are biased by complexity, learning order, position, and morecited by 22
2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
2022Learning Robust Representation for Joint Grading of Ophthalmic Diseases via Adaptive Curriculum and Feature Disentanglementcited by 20
2024When does compositional structure yield compositional generalization? A kernel theorycited by 19
2022Discrete Key-Value Bottleneckcited by 18
2022HACA3: A Unified Approach for Multi-site MR Image Harmonizationcited by 17
2023TP2O: Creative Text Pair-to-Object Generation using Balance Swap-Samplingcited by 16
2024Analyzing (In)Abilities of SAEs via Formal Languagescited by 16
2022When are Post-hoc Conceptual Explanations Identifiable?cited by 14
2023Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanismscited by 14
2022Inductive Biases for Object-Centric Representations in the Presence of Complex Texturescited by 13
2021The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agentscited by 12
2022Disentangling A Single MR Modalitycited by 12
2023ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representationscited by 10
2023Identifying Semantic Component for Robust Molecular Property Predictioncited by 10
2024Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformerscited by 10
2022Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representationscited by 9
2024Disentangling representations of retinal images with generative modelscited by 8
2021Be More Active! Understanding the Differences between Mean and Sampled Representations of Variational Autoencoderscited by 7
2022Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domaincited by 7
2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
2023Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Modelscited by 6
2022A Comprehensive Review of Trends, Applications and Challenges In Out-of-Distribution Detectioncited by 5
2024Towards the Reusability and Compositionality of Causal Representationscited by 5
2022Disentangled Learning of Stance and Aspect Topics for Vaccine Attitude Detection in Social Mediacited by 4
2022Exploiting Personalized Invariance for Better Out-of-distribution Generalization in Federated Learningcited by 4
2023Disentanglement Learning via Topologycited by 4
2024Towards Controllable Time Series Generationcited by 4
2025Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learningcited by 4
2025When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspectivecited by 4
2022Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separationcited by 3

50 most cited of 94 All 94 (JSON)