My research interests lie in machine learning and artificial intelligence, especially in causal discovery and causality-based learning. I develop methods for automated causal discovery from various kinds of data, investigate learning problems including transfer learning, concept learning, and deep learning from a causal view, and study philosophical foundations of causation and various machine learning tasks. Recently I have been focusing on causal representation learning. On the application side, I am interested in neuroscience, computer vision, computational finance, and climate analysis.