Disentangled representation learning has been proposed as an approach to learning
general representations even in the absence of, or with limited, supervision. A good general …

Causal representation learning seeks to extract high-level latent factors from low-level
sensory data. Most existing methods rely on observational data and structural assumptions …

Despite recent success in using the invariance principle for out-of-distribution (OOD)
generalization on Euclidean data (eg, images), studies on graph data are still limited …

Contrastive learning is a popular form of self-supervised learning that encourages
augmentations (views) of the same input to have more similar representations compared to …

Learning high-level causal representations together with a causal model from unstructured
low-level data such as pixels is impossible from observational data alone. We prove under …

Time series forecasting has been a widely explored task of great importance in many
applications. However, it is common that real-world time series data are recorded in a short …

Temporal data, representing chronological observations of complex systems, has always
been a typical data structure that can be widely generated by many domains, such as …

Understanding the latent causal factors of a dynamical system from visual observations is
considered a crucial step towards agents reasoning in complex environments. In this paper …

We study causal representation learning, the task of inferring latent causal variables and
their causal relations from high-dimensional functions (“mixtures”) of the variables. Prior …

This work introduces a novel principle we call disentanglement via mechanism sparsity
regularization, which can be applied when the latent factors of interest depend sparsely on …