Yang, M; Cai, X; Liu, F; Zhang, W; Wang, J; (2023) Specify Robust Causal Representation from Mixed Observations. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. (pp. pp. 2978-2987). ACM (Association for Computing Machinery)

Preview

PDF 3580305.3599512.pdf - Published Version Download (1MB) | Preview

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.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item