[HTML][HTML] Learning disentangled representations in the imaging domain

X Liu, P Sanchez, S Thermos, AQ O'Neil… - Medical Image …, 2022 - Elsevier
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 …

Interventional causal representation learning

K Ahuja, D Mahajan, Y Wang… - … conference on machine …, 2023 - proceedings.mlr.press
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 …

Learning causally invariant representations for out-of-distribution generalization on graphs

Y Chen, Y Zhang, Y Bian, H Yang… - Advances in …, 2022 - proceedings.neurips.cc
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 …

Understanding contrastive learning requires incorporating inductive biases

N Saunshi, J Ash, S Goel, D Misra… - International …, 2022 - proceedings.mlr.press
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 …

Weakly supervised causal representation learning

J Brehmer, P De Haan, P Lippe… - Advances in Neural …, 2022 - proceedings.neurips.cc
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 …

Generative time series forecasting with diffusion, denoise, and disentanglement

Y Li, X Lu, Y Wang, D Dou - Advances in Neural …, 2022 - proceedings.neurips.cc
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 …

Causal discovery from temporal data: An overview and new perspectives

C Gong, D Yao, C Zhang, W Li, J Bi - arXiv preprint arXiv:2303.10112, 2023 - arxiv.org
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 …

Citris: Causal identifiability from temporal intervened sequences

P Lippe, S Magliacane, S Löwe… - International …, 2022 - proceedings.mlr.press
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 …

Nonparametric identifiability of causal representations from unknown interventions

J von Kügelgen, M Besserve… - Advances in …, 2024 - proceedings.neurips.cc
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 …

Disentanglement via mechanism sparsity regularization: A new principle for nonlinear ICA

S Lachapelle, P Rodriguez, Y Sharma… - … on Causal Learning …, 2022 - proceedings.mlr.press
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 …