Amortized Counterfactual Prediction with Graph Neural Networks
cs.LG, cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/Zelos1/CFGNP
Sources
- Translation Equivariant Transformer Neural Processes
- How Attentive are Graph Attention Networks?
- Counterfactual Learning with Multioutput Deep Kernels
- Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning
- Neural Processes
- Causal normalizing flows: from theory to practice
- Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
- Causal Autoregressive Flows
- Attentive Neural Processes
- Deep Backtracking Counterfactuals for Causally Compliant Explanations
- Learning Structural Causal Models from Ordering: Identifiable Flow Models
- DoubleGen: Debiased Generative Modeling of Counterfactuals
- Counterfactual Identifiability of Bijective Causal Models
- Deep Structural Causal Models for Tractable Counterfactual Inference
- Diffusion Counterfactual Generation with Semantic Abduction
- Counterfactual Identifiability via Dynamic Optimal Transport
- VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries
- What Counterfactuals Can Be Tested
- Causal Feature Selection via Orthogonal Search
- Counterfactual Generative Modeling with Variational Causal Inference
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks