mlsanityData to 7 Oct 2026

Efficiently Disentangle Causal Representations

arXiv 2201.01942 ↗First posted 6 Jan 2022cs.LG stat.MLcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 47 references that are in the map. First posted on arXiv 6 Jan 2022.

Builds on

18 of 47 references.

References · 18

  1. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  2. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  3. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  4. 2016Learning Representations for Counterfactual Inferencecited by 327
  5. 2018Towards a Definition of Disentangled Representationscited by 294
  6. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 278
  7. 2013Learning Bayesian Networks: The Combination of Knowledge and Statistical Datacited by 185
  8. 2018Compositional Attention Networks for Machine Reasoningcited by 183
  9. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  10. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  11. 2017Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributionscited by 125
  12. 2017Learning Independent Causal Mechanismscited by 104
6 more
  1. 2018Learning Plannable Representations with Causal InfoGANcited by 56
  2. 2019Causal Reasoning from Meta-reinforcement Learningcited by 53
  3. 2019Compositional Generalization for Primitive Substitutionscited by 48
  4. 2014Distinguishing cause from effect using observational data: methods and benchmarkscited by 33
  5. 2013Learning Bayesian Networks with Local Structurecited by 9
  6. 2013Using Causal Information and Local Measures to Learn Bayesian Networkscited by 1

Built on by

Not cited yet.