Relational Structural Causal Models
Quick Answer
This paper shows that This work introduces relational structural causal models, extending Pearl's framework to learn causal relationships in variable object settings.
Quick Take
This work introduces relational structural causal models, extending Pearl's framework to learn causal relationships in variable object settings. It establishes identification criteria for causal and observational queries and proposes relational neural causal models that outperform traditional methods in simulated traffic scenarios.
Key Points
- Relational structural causal models extend traditional causal models for variable object environments.
- Identification of causal and observational queries requires additional assumptions.
- Relational causal graphs and symbolic identification criteria are defined for better analysis.
- Relational neural causal models outperform non-relational baselines in traffic simulations.
Paper Resources
Article Excerpt
From source RSS / original summaryarXiv:2606. 14892v1 Announce Type: new 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.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Arbor: Tree Search as a Cognition Layer for Autonomous Agents
Arbor introduces a multi-agent framework utilizing structured tree search for optimizing LLM inference, achieving up to 193% throughput-latency improvement compared to vendor-optimized systems. It employs an Orchestrator and Critic agent for stability and coordination, demonstrating hardware-agnostic performance with minimal variance.