High Fidelity Image Counterfactuals with Probabilistic Causal Models
- URL: http://arxiv.org/abs/2306.15764v2
- Date: Tue, 18 Jul 2023 15:07:01 GMT
- Title: High Fidelity Image Counterfactuals with Probabilistic Causal Models
- Authors: Fabio De Sousa Ribeiro, Tian Xia, Miguel Monteiro, Nick Pawlowski, Ben
Glocker
- Abstract summary: We present a causal generative modelling framework for accurate estimation of high fidelity image counterfactuals with deep structural causal models.
We leverage ideas from causal mediation analysis and advances in generative modelling to design new deep causal mechanisms for structured variables in causal models.
- Score: 25.87025672100077
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We present a general causal generative modelling framework for accurate
estimation of high fidelity image counterfactuals with deep structural causal
models. Estimation of interventional and counterfactual queries for
high-dimensional structured variables, such as images, remains a challenging
task. We leverage ideas from causal mediation analysis and advances in
generative modelling to design new deep causal mechanisms for structured
variables in causal models. Our experiments demonstrate that our proposed
mechanisms are capable of accurate abduction and estimation of direct, indirect
and total effects as measured by axiomatic soundness of counterfactuals.
Related papers
- Revisiting Spurious Correlation in Domain Generalization [12.745076668687748]
We build a structural causal model (SCM) to describe the causality within data generation process.
We further conduct a thorough analysis of the mechanisms underlying spurious correlation.
In this regard, we propose to control confounding bias in OOD generalization by introducing a propensity score weighted estimator.
arXiv Detail & Related papers (2024-06-17T13:22:00Z) - Learning Discrete Concepts in Latent Hierarchical Models [73.01229236386148]
Learning concepts from natural high-dimensional data holds potential in building human-aligned and interpretable machine learning models.
We formalize concepts as discrete latent causal variables that are related via a hierarchical causal model.
We substantiate our theoretical claims with synthetic data experiments.
arXiv Detail & Related papers (2024-06-01T18:01:03Z) - Towards Understanding How Transformer Perform Multi-step Reasoning with Matching Operation [52.77133661679439]
Investigating internal reasoning mechanisms of large language models can help us design better model architectures and training strategies.
We investigate the matching mechanism employed by Transformer for multi-step reasoning on a constructed dataset.
We propose a conjecture on the upper bound of the model's reasoning ability based on this phenomenon.
arXiv Detail & Related papers (2024-05-24T07:41:26Z) - Distribution-consistency Structural Causal Models [6.276417011421679]
We introduce a novel textitdistribution-consistency assumption, and in alignment with it, we propose the Distribution-consistency Structural Causal Models (DiscoSCMs)
To concretely reveal the enhanced model capacity, we introduce a new identifiable causal parameter, textitthe probability of consistency, which holds practical significance within DiscoSCM alone.
arXiv Detail & Related papers (2024-01-29T06:46:15Z) - A physics-informed machine learning model for reconstruction of dynamic
loads [0.0]
This paper presents a physics-informed machine-learning framework for reconstructing dynamic forces based on measured deflections, velocities, or accelerations.
The framework can work with incomplete and contaminated data and offers a natural regularization approach to account for noise measurement system.
Uses of the developed framework include design models and assumptions, as well as prognosis of responses to assist in damage detection and health monitoring.
arXiv Detail & Related papers (2023-08-15T18:33:58Z) - Quantify the Causes of Causal Emergence: Critical Conditions of
Uncertainty and Asymmetry in Causal Structure [0.5372002358734439]
Investigation of causal relationships based on statistical and informational theories have posed an interesting and valuable challenge to large-scale models.
This paper introduces a framework for assessing numerical conditions of Causal Emergence as theoretical constraints of its occurrence.
arXiv Detail & Related papers (2022-12-03T06:35:54Z) - On the Generalization and Adaption Performance of Causal Models [99.64022680811281]
Differentiable causal discovery has proposed to factorize the data generating process into a set of modules.
We study the generalization and adaption performance of such modular neural causal models.
Our analysis shows that the modular neural causal models outperform other models on both zero and few-shot adaptation in low data regimes.
arXiv Detail & Related papers (2022-06-09T17:12:32Z) - Estimation of Bivariate Structural Causal Models by Variational Gaussian
Process Regression Under Likelihoods Parametrised by Normalising Flows [74.85071867225533]
Causal mechanisms can be described by structural causal models.
One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
arXiv Detail & Related papers (2021-09-06T14:52:58Z) - Robustness of Model Predictions under Extension [3.766702945560518]
A caveat to using models for analysis is that predicted causal effects and conditional independences may not be robust under model extensions.
We show how to use the technique of causal ordering to efficiently assess the robustness of qualitative model predictions.
For dynamical systems at equilibrium, we demonstrate how novel insights help to select appropriate model extensions.
arXiv Detail & Related papers (2020-12-08T20:21:03Z) - Structural Causal Models Are (Solvable by) Credal Networks [70.45873402967297]
Causal inferences can be obtained by standard algorithms for the updating of credal nets.
This contribution should be regarded as a systematic approach to represent structural causal models by credal networks.
Experiments show that approximate algorithms for credal networks can immediately be used to do causal inference in real-size problems.
arXiv Detail & Related papers (2020-08-02T11:19:36Z) - A Critical View of the Structural Causal Model [89.43277111586258]
We show that one can identify the cause and the effect without considering their interaction at all.
We propose a new adversarial training method that mimics the disentangled structure of the causal model.
Our multidimensional method outperforms the literature methods on both synthetic and real world datasets.
arXiv Detail & Related papers (2020-02-23T22:52:28Z)
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.