Relational Structural Causal Models

2026-06-12

AI Summary

This work addresses causal reasoning in dynamic environments where objects and their relationships evolve over time by proposing the Relational Structural Causal Model (RSCM), which formalizes, for the first time, the problem of causal identifiability in relational settings. By introducing relational causal graphs and symbolic identification criteria, the framework enables both interventional and counterfactual reasoning and generalizes to novel object configurations involving unobserved confounders. Building upon this foundation, the authors develop a provably correct relational neural causal network. Empirical evaluation in a dynamic traffic simulation—featuring vehicles, traffic signals, and pedestrians—demonstrates that the proposed model significantly outperforms non-relational baseline approaches.

Abstract

An artificial intelligence must have a model of its environment that is causal, supporting reasoning about interventions and counterfactuals, and also combinatorial, supporting generalization to unseen combinations of objects. In this work, we formally study when and how such a model can be learned. We develop relational structural causal models, extending structural causal models (Pearl 2009) to settings where objects and their relations vary. First, we show how answers to not only causal but also observational queries about unseen combinations of objects can not be identified without further assumptions. To enable such identification--including in the presence of unobserved confounding--we define relational causal graphs and derive symbolic identification criteria. Finally, we propose relational neural causal models, a provably correct approach that outperforms non-relational baselines on simulated traffic scenes with varying cars, signals, and pedestrians.

Problem

• relational structural causal models
• causal reasoning
• combinatorial generalization
• unobserved confounding
• structural causal models

Innovation

• relational structural causal models
• causal identification
• unobserved confounding
• relational neural causal models
• combinatorial generalization