# Disentangling Factors of Variation Using Few Labels

arXiv: https://arxiv.org/abs/1905.01258 · HTML: https://mlsanity.com/paper/1905.01258/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2019.

## Built on by (most cited first, 30 of 57)

- [Desiderata for Representation Learning: A Causal Perspective](https://mlsanity.com/paper/2109.03795/) (2021)
- [No Representation Rules Them All in Category Discovery](https://mlsanity.com/paper/2311.17055/) (2023)
- [Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems](https://mlsanity.com/paper/2206.06169/) (2022)
- [Self-Supervised Learning Disentangled Group Representation as Feature](https://mlsanity.com/paper/2110.15255/) (2021)
- [Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning](https://mlsanity.com/paper/2211.14666/) (2022)
- [Subspace Identification for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2310.04723/) (2023)
- [Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation](https://mlsanity.com/paper/2205.03962/) (2022)
- [Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment](https://mlsanity.com/paper/2305.12218/) (2023)
- [An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild](https://mlsanity.com/paper/2106.15610/) (2021)
- [Where and What? Examining Interpretable Disentangled Representations](https://mlsanity.com/paper/2104.05622/) (2021)
- [Learning disentangled representations via product manifold projection](https://mlsanity.com/paper/2103.01638/) (2021)
- [On the Versatile Uses of Partial Distance Correlation in Deep Learning](https://mlsanity.com/paper/2207.09684/) (2022)
- [Unsupervised Learning of Equivariant Structure from Sequences](https://mlsanity.com/paper/2210.05972/) (2022)
- [Towards a Unified Framework of Contrastive Learning for Disentangled Representations](https://mlsanity.com/paper/2311.04774/) (2023)
- [Compositional Image Decomposition with Diffusion Models](https://mlsanity.com/paper/2406.19298/) (2024)
- [Multi-objective Deep Data Generation with Correlated Property Control](https://mlsanity.com/paper/2210.01796/) (2022)
- [Identifying Semantic Component for Robust Molecular Property Prediction](https://mlsanity.com/paper/2311.04837/) (2023)
- [Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition](https://mlsanity.com/paper/2202.07260/) (2022)
- [Language Agents Meet Causality -- Bridging LLMs and Causal World Models](https://mlsanity.com/paper/2410.19923/) (2024)
- [Disentangled Generative Models for Robust Prediction of System Dynamics](https://mlsanity.com/paper/2108.11684/) (2021)
- [Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement](https://mlsanity.com/paper/2105.08970/) (2021)
- [GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain](https://mlsanity.com/paper/2503.22397/) (2025)
- [From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?](https://mlsanity.com/paper/2512.15134/) (2025)
- [On Disentanglement in Gaussian Process Variational Autoencoders](https://mlsanity.com/paper/2102.05507/) (2021)
- [Leveraging Relational Information for Learning Weakly Disentangled Representations](https://mlsanity.com/paper/2205.10056/) (2022)
- [Retrieval-based Disentangled Representation Learning with Natural Language Supervision](https://mlsanity.com/paper/2212.07699/) (2022)
- [Finding simplicity: unsupervised discovery of features, patterns, and order parameters via shift-invariant variational autoencoders](https://mlsanity.com/paper/2106.12472/) (2021)
- [On the relationship between disentanglement and multi-task learning](https://mlsanity.com/paper/2110.03498/) (2021)
- [Blackbird's language matrices (BLMs): a new benchmark to investigate disentangled generalisation in neural networks](https://mlsanity.com/paper/2205.10866/) (2022)
- [Towards a Solution to Bongard Problems: A Causal Approach](https://mlsanity.com/paper/2206.07196/) (2022)

## Abstract (arXiv)

Learning disentangled representations is considered a cornerstone problem in representation learning. Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to consistently learn disentangled representations. However, in many practical settings, one might have access to a limited amount of supervision, for example through manual labeling of (some) factors of variation in a few training examples. In this paper, we investigate the impact of such supervision on state-of-the-art disentanglement methods and perform a large scale study, training over 52000 models under well-defined and reproducible experimental conditions. We observe that a small number of labeled examples (0.01--0.5% of the data set), with potentially imprecise and incomplete labels, is sufficient to perform model selection on state-of-the-art unsupervised models. Further, we investigate the benefit of incorporating supervision into the training process. Overall, we empirically validate that with little and imprecise supervision it is possible to reliably learn disentangled representations.