Track synthesis, materials and catalysis as it is published.
Search papers, labs, and topics across Lattice.
This paper introduces the Counterfactual Graph Neural Process (CFGNP), an end-to-end approach that directly answers counterfactual queries from observational data without explicit causal graph estimation. CFGNP leverages Graph Neural Networks with restricted cross-world message passing to mitigate error propagation from graph estimation. Experimental results demonstrate superior predictive performance over existing methods on synthetic and image-based benchmarks, including a significant MSE reduction on the German Loan dataset and strong generalization to larger graphs without retraining.
Counterfactual predictions can be made with significantly higher accuracy and generalization by bypassing explicit causal graph estimation and directly learning from observational data via amortized GNNs.
Counterfactual inference asks how an observed outcome might have differed under different circumstances, such as whether a patient would have recovered had they received a different treatment. Such questions arise whenever decisions depend on the outcomes of alternatives that were not observed. Answering counterfactual queries generally requires knowledge of the underlying causal structure, which is often unavailable in practice. A common approach is therefore to first estimate the causal graph from observational data and then perform counterfactual inference. However, errors in the estimated causal graph can propagate to downstream counterfactual predictions. To address this challenge, we introduce the Counterfactual Graph Neural Process (CFGNP), an end-to-end approach that answers counterfactual queries directly from observational data without first estimating a causal graph. CFGNP uses Graph Neural Networks (GNNs) to exploit the dual-graph structure by restricting cross-world message passing to corresponding factual--counterfactual variables. Across synthetic and image-based benchmarks, CFGNP achieves stronger predictive performance than existing approaches, including on the German Loan benchmark, where it reduces MSE from $4.51 \times 10^{-2}$ to $0.19 \times 10^{-2}$. Furthermore, on synthetic causal graphs, a model trained only on 10-node graphs maintains strong predictive performance on graphs with up to 30 nodes, without retraining.