Specify Robust Causal Representation from Mixed Observations

Authors:
  • MYMengyue Yang
    Mengyue Yang
  • XCXinyu Cai
    Xinyu Cai
  • FLFurui Liu
    Furui Liu
  • WZWeinan Zhang
    Weinan Zhang
  • JWJun Wang
    Jun Wang

Abstract
Learning representations purely from observations concerns the problem of learning a low-dimensional, compact representation which is beneficial to prediction models. Under the hypothesis that the intrinsic latent factors follow some casual generative models, we argue that by learning a causal representation, which is the minimal sufficient causes of the whole system, we can improve the robustness and generalization performance of machine learning models. In this paper, we develop a learning method to learn such representation from observational data by regularizing the learning procedure with mutual information measures, according to the hypothetical factored causal graph. We theoretically and empirically show that the models trained with the learned causal representations are more robust under adversarial attacks and distribution shifts compared with baselines. The supplementary materials are available at https://github.com/ymy $4323460 / \mathrm{CaRI} /$.
All Related Versions

This publication has 9 references indexed in Scilit: