论文标题
学会诱导因果结构
Learning to Induce Causal Structure
论文作者
论文摘要
因果诱导中的基本挑战是在观察性和/或介入数据下推断基础图结构。大多数现有的因果诱导算法通过生成候选图并使用基于得分的方法（包括连续优化）或独立测试来评估它们。在我们的工作中，我们将推理过程视为黑匣子，并设计了一种神经网络体系结构，该神经网络体系结构从观测数据和介入数据中学习映射到图形结构，通过对合成图的监督培训。博学的模型将其推广到新的合成图，对于训练测试的分布变化是可靠的，并且可以在自然图上实现最先进的表现，以达到低样本复杂性。
The fundamental challenge in causal induction is to infer the underlying graph structure given observational and/or interventional data. Most existing causal induction algorithms operate by generating candidate graphs and evaluating them using either score-based methods (including continuous optimization) or independence tests. In our work, we instead treat the inference process as a black box and design a neural network architecture that learns the mapping from both observational and interventional data to graph structures via supervised training on synthetic graphs. The learned model generalizes to new synthetic graphs, is robust to train-test distribution shifts, and achieves state-of-the-art performance on naturalistic graphs for low sample complexity.
