提出关系型因果模型，让AI能推理新组合下的因果关系。
Relational Structural Causal Models
- 将因果模型扩展到可变对象与关系的场景
- 在未见物体组合下仍能准确识别因果效应
- 适合需要泛化能力的智能体系统研究
人工智能需具备环境的因果模型，以支持干预和反事实推理，并具备组合性以泛化至未见的对象组合。本文正式研究此类模型何时可学习。提出关系型结构因果模型，扩展了Pearl（2009）的结构因果模型，适用于对象及其关系动态变化的场景。首先，证明在无额外假设下，对未见组合的因果与观测查询无法识别。为实现识别（包括存在未观测混杂时），定义关系型因果图并推导出符号化识别准则。最后，提出关系型神经因果模型，一种可证明正确的方法，在包含不同车辆、信号灯与行人的模拟交通场景中，性能优于非关系基线。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。