# DEFT: Distilling Entangled Factors by Preventing Information Diffusion

arXiv: https://arxiv.org/abs/2102.03986 · HTML: https://mlsanity.com/paper/2102.03986/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 8 Feb 2021.

## Builds on (most cited first, 17 of 17)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Understanding disentangling in β-VAE](https://mlsanity.com/paper/1804.03599/) (2018)
- [Towards a Definition of Disentangled Representations](https://mlsanity.com/paper/1812.02230/) (2018)
- [Variational Inference of Disentangled Latent Concepts from Unlabeled Observations](https://mlsanity.com/paper/1711.00848/) (2017)
- [DARLA: Improving Zero-Shot Transfer in Reinforcement Learning](https://mlsanity.com/paper/1707.08475/) (2017)
- [Fader Networks: Manipulating Images by Sliding Attributes](https://mlsanity.com/paper/1706.00409/) (2017)
- [Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness](https://mlsanity.com/paper/1811.00007/) (2018)
- [Learning Deep Disentangled Embeddings with the F-Statistic Loss](https://mlsanity.com/paper/1802.05312/) (2018)
- [On Disentangled Representations Learned From Correlated Data](https://mlsanity.com/paper/2006.07886/) (2020)
- [Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)](https://mlsanity.com/paper/2001.04872/) (2020)
- [Learning Disentangled Joint Continuous and Discrete Representations](https://mlsanity.com/paper/1804.00104/) (2018)
- [Theory and Evaluation Metrics for Learning Disentangled Representations](https://mlsanity.com/paper/1908.09961/) (2019)
- [Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learning](https://mlsanity.com/paper/1904.10056/) (2019)
- [Learning Discrete and Continuous Factors of Data via Alternating Disentanglement](https://mlsanity.com/paper/1905.09432/) (2019)

## Built on by (most cited first, 1 of 1)

- [Variantional autoencoder with decremental information bottleneck for disentanglement](https://mlsanity.com/paper/2303.12959/) (2023)

## Abstract (arXiv)

Disentanglement is a highly desirable property of representation owing to its similarity to human understanding and reasoning. Many works achieve disentanglement upon information bottlenecks (IB). Despite their elegant mathematical foundations, the IB branch usually exhibits lower performance. In order to provide an insight into the problem, we develop an annealing test to calculate the information freezing point (IFP), which is a transition state to freeze information into the latent variables. We also explore these clues or inductive biases for separating the entangled factors according to the differences in the IFP distributions. We found the existing approaches suffer from the information diffusion problem, according to which the increased information diffuses in all latent variables. Based on this insight, we propose a novel disentanglement framework, termed the distilling entangled factor (DEFT), to address the information diffusion problem by scaling backward information. DEFT applies a multistage training strategy, including multigroup encoders with different learning rates and piecewise disentanglement pressure, to disentangle the factors stage by stage. We evaluate DEFT on three variants of dSprite and SmallNORB, which show low-variance and high-level disentanglement scores. Furthermore, the experiment under the correlative factors shows incapable of TC-based approaches. DEFT also exhibits a competitive performance in the unsupervised setting.