CITRIS: Causal Identifiability from Temporal Intervened Sequences
- URL: http://arxiv.org/abs/2202.03169v1
- Date: Mon, 7 Feb 2022 13:55:36 GMT
- Title: CITRIS: Causal Identifiability from Temporal Intervened Sequences
- Authors: Phillip Lippe, Sara Magliacane, Sindy L\"owe, Yuki M. Asano, Taco
Cohen, Efstratios Gavves
- Abstract summary: We propose CITRIS, a variational autoencoder framework that learns causal representations from temporal sequences of images.
In experiments on 3D rendered image sequences, CITRIS outperforms previous methods on recovering the underlying causal variables.
- Score: 36.358968799947924
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Understanding the latent causal factors of a dynamical system from visual
observations is a crucial step towards agents reasoning in complex
environments. In this paper, we propose CITRIS, a variational autoencoder
framework that learns causal representations from temporal sequences of images
in which underlying causal factors have possibly been intervened upon. In
contrast to the recent literature, CITRIS exploits temporality and observing
intervention targets to identify scalar and multidimensional causal factors,
such as 3D rotation angles. Furthermore, by introducing a normalizing flow,
CITRIS can be easily extended to leverage and disentangle representations
obtained by already pretrained autoencoders. Extending previous results on
scalar causal factors, we prove identifiability in a more general setting, in
which only some components of a causal factor are affected by interventions. In
experiments on 3D rendered image sequences, CITRIS outperforms previous methods
on recovering the underlying causal variables. Moreover, using pretrained
autoencoders, CITRIS can even generalize to unseen instantiations of causal
factors, opening future research areas in sim-to-real generalization for causal
representation learning.
Related papers
- Targeted Reduction of Causal Models [55.11778726095353]
Causal Representation Learning offers a promising avenue to uncover interpretable causal patterns in simulations.
We introduce Targeted Causal Reduction (TCR), a method for condensing complex intervenable models into a concise set of causal factors.
Its ability to generate interpretable high-level explanations from complex models is demonstrated on toy and mechanical systems.
arXiv Detail & Related papers (2023-11-30T15:46:22Z) - Nonlinearity, Feedback and Uniform Consistency in Causal Structural
Learning [0.8158530638728501]
Causal Discovery aims to find automated search methods for learning causal structures from observational data.
This thesis focuses on two questions in causal discovery: (i) providing an alternative definition of k-Triangle Faithfulness that (i) is weaker than strong faithfulness when applied to the Gaussian family of distributions, and (ii) under the assumption that the modified version of Strong Faithfulness holds.
arXiv Detail & Related papers (2023-08-15T01:23:42Z) - Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms [17.074858228123706]
We propose a framework for learning causally disentangled representations supervised by causally related observed labels.
We show that our framework induces highly disentangled causal factors, improves interventional robustness, and is compatible with counterfactual generation.
arXiv Detail & Related papers (2023-06-02T00:28:48Z) - Causal Triplet: An Open Challenge for Intervention-centric Causal
Representation Learning [98.78136504619539]
Causal Triplet is a causal representation learning benchmark featuring visually more complex scenes.
We show that models built with the knowledge of disentangled or object-centric representations significantly outperform their distributed counterparts.
arXiv Detail & Related papers (2023-01-12T17:43:38Z) - iCITRIS: Causal Representation Learning for Instantaneous Temporal
Effects [36.358968799947924]
Causal representation learning is the task of identifying the underlying causal variables and their relations from high-dimensional observations.
We propose iCITRIS, a causal representation learning method that can handle instantaneous effects in temporal sequences.
In experiments on three video datasets, iCITRIS accurately identifies the causal factors and their causal graph.
arXiv Detail & Related papers (2022-06-13T13:56:40Z) - Discovering Latent Causal Variables via Mechanism Sparsity: A New
Principle for Nonlinear ICA [81.4991350761909]
Independent component analysis (ICA) refers to an ensemble of methods which formalize this goal and provide estimation procedure for practical application.
We show that the latent variables can be recovered up to a permutation if one regularizes the latent mechanisms to be sparse.
arXiv Detail & Related papers (2021-07-21T14:22:14Z) - Systematic Evaluation of Causal Discovery in Visual Model Based
Reinforcement Learning [76.00395335702572]
A central goal for AI and causality is the joint discovery of abstract representations and causal structure.
Existing environments for studying causal induction are poorly suited for this objective because they have complicated task-specific causal graphs.
In this work, our goal is to facilitate research in learning representations of high-level variables as well as causal structures among them.
arXiv Detail & Related papers (2021-07-02T05:44:56Z) - Verifying the Causes of Adversarial Examples [5.381050729919025]
The robustness of neural networks is challenged by adversarial examples that contain almost imperceptible perturbations to inputs.
We present a collection of potential causes of adversarial examples and verify (or partially verify) them through carefully-designed controlled experiments.
Our experiment results show that geometric factors tend to be more direct causes and statistical factors magnify the phenomenon.
arXiv Detail & Related papers (2020-10-19T16:17:20Z) - CausalVAE: Structured Causal Disentanglement in Variational Autoencoder [52.139696854386976]
The framework of variational autoencoder (VAE) is commonly used to disentangle independent factors from observations.
We propose a new VAE based framework named CausalVAE, which includes a Causal Layer to transform independent factors into causal endogenous ones.
Results show that the causal representations learned by CausalVAE are semantically interpretable, and their causal relationship as a Directed Acyclic Graph (DAG) is identified with good accuracy.
arXiv Detail & Related papers (2020-04-18T20:09:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.