Karimi Mamaghan Amir Mohammad, Dittadi Andrea, Bauer Stefan, Johansson Karl Henrik, Quinzan Francesco
Division of Decision and Control Systems (DCS), KTH Royal Institute of Technology, 114 28 Stockholm, Sweden.
Helmholtz AI, 85764 Munich, Germany.
Entropy (Basel). 2024 Jun 28;26(7):556. doi: 10.3390/e26070556.
Causal reasoning can be considered a cornerstone of intelligent systems. Having access to an underlying causal graph comes with the promise of cause-effect estimation and the identification of efficient and safe interventions. However, learning causal representations remains a major challenge, due to the complexity of many real-world systems. Previous works on causal representation learning have mostly focused on Variational Auto-Encoders (VAEs). These methods only provide representations from a point estimate, and they are less effective at handling high dimensions. To overcome these problems, we propose a Diffusion-based Causal Representation Learning (DCRL) framework which uses diffusion-based representations for causal discovery in the latent space. DCRL provides access to both single-dimensional and infinite-dimensional latent codes, which encode different levels of information. In a first proof of principle, we investigate the use of DCRL for causal representation learning in a weakly supervised setting. We further demonstrate experimentally that this approach performs comparably well in identifying the latent causal structure and causal variables.
因果推理可被视为智能系统的基石。能够获取潜在的因果图有望进行因果效应估计以及识别有效且安全的干预措施。然而，由于许多现实世界系统的复杂性，学习因果表示仍然是一项重大挑战。先前关于因果表示学习的工作大多集中在变分自编码器（VAE）上。这些方法仅从点估计提供表示，并且在处理高维数据时效果较差。为了克服这些问题，我们提出了一种基于扩散的因果表示学习（DCRL）框架，该框架在潜在空间中使用基于扩散的表示进行因果发现。DCRL提供了对单维以及无限维潜在代码的访问，这些代码编码了不同层次的信息。在第一个原理验证中，我们研究了在弱监督设置下使用DCRL进行因果表示学习。我们进一步通过实验证明，这种方法在识别潜在因果结构和因果变量方面表现相当出色。
