Relational Structural Causal Models

Computer Science > Artificial Intelligence [Submitted on 12 Jun 2026] Relational Structural Causal Models Adiba Ejaz, Elias Bareinboim 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. Comments: Proceedings of the Forty-Third International Conference on Machine Learning Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Social and Information Networks (cs.SI); Machine Learning (stat.ML) Cite as: arXiv:2606.14892 [cs.AI]   (or arXiv:2606.14892v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.14892 Focus to learn more Submission history From: Adiba Ejaz [view email] [v1] Fri, 12 Jun 2026 18:54:06 UTC (2,113 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.LG cs.SI stat stat.ML References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)