# Relational Structural Causal Models

arXiv: https://arxiv.org/abs/2606.14892 · HTML: https://mlsanity.com/paper/2606.14892/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 142 references that are in the map.
- First posted on arXiv 12 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting](https://mlsanity.com/paper/1802.07007/) (2018)
- [On the Measure of Intelligence](https://mlsanity.com/paper/1911.01547/) (2019)
- [Topological Deep Learning: Going Beyond Graph Data](https://mlsanity.com/paper/2206.00606/) (2022)
- [Relational Deep Reinforcement Learning](https://mlsanity.com/paper/1806.01830/) (2018)
- [Vision Language Models are Biased](https://mlsanity.com/paper/2505.23941/) (2025)
- [Visual Representation Learning Does Not Generalize Strongly Within the Same Domain](https://mlsanity.com/paper/2107.08221/) (2021)
- [A Framework For Contrastive Self-Supervised Learning And Designing A New Approach](https://mlsanity.com/paper/2009.00104/) (2020)
- [Griffin: Towards a Graph-Centric Relational Database Foundation Model](https://mlsanity.com/paper/2505.05568/) (2025)
- [Relational inductive bias for physical construction in humans and machines](https://mlsanity.com/paper/1806.01203/) (2018)
- [Relating Graph Neural Networks to Structural Causal Models](https://mlsanity.com/paper/2109.04173/) (2021)
- [Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data](https://mlsanity.com/paper/2510.06377/) (2025)
- [Relational Graph Transformer](https://mlsanity.com/paper/2505.10960/) (2025)
- [Large Language Models are Good Relational Learners](https://mlsanity.com/paper/2506.05725/) (2025)
- [Dyn-O: Building Structured World Models with Object-Centric Representations](https://mlsanity.com/paper/2507.03298/) (2025)
- [Discovering objects and their relations from entangled scene representations](https://mlsanity.com/paper/1702.05068/) (2017)
- [Hierarchical Causal Models](https://mlsanity.com/paper/2401.05330/) (2024)
- [Hierarchical Protein Function Prediction with Tail-GNNs](https://mlsanity.com/paper/2007.12804/) (2020)
- [Answering Visual-Relational Queries in Web-Extracted Knowledge Graphs](https://mlsanity.com/paper/1709.02314/) (2017)

## Abstract (arXiv)

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.