LGCVFeb 21, 2022

Diffusion Causal Models for Counterfactual Estimation

arXiv:2202.10166v1111 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the problem of causal inference for high-dimensional data, which is important for researchers in machine learning and causal modeling, though it appears incremental as it builds on existing generative methods.

The authors tackled the challenge of counterfactual estimation from high-dimensional observational imaging data by proposing Diff-SCM, a deep structural causal model based on generative energy-based models, which produced more realistic and minimal counterfactuals than baselines on MNIST and ImageNet data.

We consider the task of counterfactual estimation from observational imaging data given a known causal structure. In particular, quantifying the causal effect of interventions for high-dimensional data with neural networks remains an open challenge. Herein we propose Diff-SCM, a deep structural causal model that builds on recent advances of generative energy-based models. In our setting, inference is performed by iteratively sampling gradients of the marginal and conditional distributions entailed by the causal model. Counterfactual estimation is achieved by firstly inferring latent variables with deterministic forward diffusion, then intervening on a reverse diffusion process using the gradients of an anti-causal predictor w.r.t the input. Furthermore, we propose a metric for evaluating the generated counterfactuals. We find that Diff-SCM produces more realistic and minimal counterfactuals than baselines on MNIST data and can also be applied to ImageNet data. Code is available https://github.com/vios-s/Diff-SCM.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes