# Efficiently Disentangle Causal Representations

arXiv: https://arxiv.org/abs/2201.01942 · HTML: https://mlsanity.com/paper/2201.01942/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 47 references that are in the map.
- First posted on arXiv 6 Jan 2022.

## Builds on (most cited first, 18 of 18)

- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Learning Representations for Counterfactual Inference](https://mlsanity.com/paper/1605.03661/) (2016)
- [Towards a Definition of Disentangled Representations](https://mlsanity.com/paper/1812.02230/) (2018)
- [Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning](https://mlsanity.com/paper/1805.08651/) (2018)
- [Learning Bayesian Networks: The Combination of Knowledge and Statistical Data](https://mlsanity.com/paper/1302.6815/) (2013)
- [Compositional Attention Networks for Machine Reasoning](https://mlsanity.com/paper/1803.03067/) (2018)
- [A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms](https://mlsanity.com/paper/1901.10912/) (2019)
- [CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training](https://mlsanity.com/paper/1709.02023/) (2017)
- [Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions](https://mlsanity.com/paper/1707.06422/) (2017)
- [Learning Independent Causal Mechanisms](https://mlsanity.com/paper/1712.00961/) (2017)
- [Learning Plannable Representations with Causal InfoGAN](https://mlsanity.com/paper/1807.09341/) (2018)
- [Causal Reasoning from Meta-reinforcement Learning](https://mlsanity.com/paper/1901.08162/) (2019)
- [Compositional Generalization for Primitive Substitutions](https://mlsanity.com/paper/1910.02612/) (2019)
- [Distinguishing cause from effect using observational data: methods and benchmarks](https://mlsanity.com/paper/1412.3773/) (2014)
- [Learning Bayesian Networks with Local Structure](https://mlsanity.com/paper/1302.3577/) (2013)
- [Using Causal Information and Local Measures to Learn Bayesian Networks](https://mlsanity.com/paper/1303.1483/) (2013)

## Abstract (arXiv)

This paper proposes an efficient approach to learning disentangled representations with causal mechanisms based on the difference of conditional probabilities in original and new distributions. We approximate the difference with models' generalization abilities so that it fits in the standard machine learning framework and can be efficiently computed. In contrast to the state-of-the-art approach, which relies on the learner's adaptation speed to new distribution, the proposed approach only requires evaluating the model's generalization ability. We provide a theoretical explanation for the advantage of the proposed method, and our experiments show that the proposed technique is 1.9--11.0× more sample efficient and 9.4--32.4 times quicker than the previous method on various tasks. The source code is available at urlhttps://github.com/yuanpeng16/EDCR.