Relational Structural Causal Models

关系型结构因果模型

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.

摘要： 人工智能必须具备一种因果性的环境模型，以支持对干预和反事实的推理；同时，该模型还需具备组合性，以支持对未见过的对象组合进行泛化。在这项工作中，我们正式研究了何时以及如何学习此类模型。

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.

我们开发了关系型结构因果模型（Relational Structural Causal Models），将结构因果模型（Pearl 2009）扩展到了对象及其关系会发生变化的场景中。首先，我们展示了在没有额外假设的情况下，如何无法识别关于未见对象组合的因果查询及观测查询的答案。

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.

为了实现这种识别（包括在存在未观测混杂因素的情况下），我们定义了关系因果图并推导出了符号识别准则。最后，我们提出了关系神经因果模型，这是一种可证明正确的方法，在包含不同车辆、信号灯和行人的模拟交通场景中，其表现优于非关系型基准模型。