Identifiability guarantees for causal disentanglement from soft interventions
Causal disentanglement aims to uncover a representation of data using latent variables that
are interrelated through a causal model. Such a representation is identifiable if the latent …
are interrelated through a causal model. Such a representation is identifiable if the latent …
Identifying representations for intervention extrapolation
The premise of identifiable and causal representation learning is to improve the current
representation learning paradigm in terms of generalizability or robustness. Despite recent …
representation learning paradigm in terms of generalizability or robustness. Despite recent …
Learning world models with identifiable factorization
Extracting a stable and compact representation of the environment is crucial for efficient
reinforcement learning in high-dimensional, noisy, and non-stationary environments …
reinforcement learning in high-dimensional, noisy, and non-stationary environments …
Structural estimation of partially observed linear non-gaussian acyclic model: A practical approach with identifiability
Conventional causal discovery approaches, which seek to uncover causal relationships
among measured variables, are typically fragile to the presence of latent variables. While …
among measured variables, are typically fragile to the presence of latent variables. While …
When and how: Learning identifiable latent states for nonstationary time series forecasting
Temporal distribution shifts are ubiquitous in time series data. One of the most popular
methods assumes that the temporal distribution shift occurs uniformly to disentangle the …
methods assumes that the temporal distribution shift occurs uniformly to disentangle the …
Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations
General intelligence requires quick adaption across tasks. While existing reinforcement
learning (RL) methods have made progress in generalization, they typically assume only …
learning (RL) methods have made progress in generalization, they typically assume only …
Learned Causal Method Prediction
For a given causal question, it is important to efficiently decide which causal inference
method to use for a given dataset. This is challenging because causal methods typically rely …
method to use for a given dataset. This is challenging because causal methods typically rely …
Learning Discrete Concepts in Latent Hierarchical Models
Learning concepts from natural high-dimensional data (eg, images) holds potential in
building human-aligned and interpretable machine learning models. Despite its …
building human-aligned and interpretable machine learning models. Despite its …
Differentiable Causal Discovery For Latent Hierarchical Causal Models
Discovering causal structures with latent variables from observational data is a fundamental
challenge in causal discovery. Existing methods often rely on constraint-based, iterative …
challenge in causal discovery. Existing methods often rely on constraint-based, iterative …
From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals
Existing methods for multi-modal time series representation learning aim to disentangle the
modality-shared and modality-specific latent variables. Although achieving notable …
modality-shared and modality-specific latent variables. Although achieving notable …