将因果图融入注意力机制，提升复杂因果推断的准确性
DAG-aware Transformer for Causal Effect Estimation
- 在注意力机制中直接嵌入因果有向无环图（DAG）
- 在合成与真实数据上均优于现有方法，支持ATE和CATE估计
- 适合处理复杂因果结构的研究者与实践者
因果推断在医疗、经济及社会科学等领域至关重要。尽管近年来基于深度学习的方法在因果效应估计方面展现出潜力，但现有方法往往难以处理复杂的因果结构，且在不同因果场景下适应性不足。本文提出一种新型基于Transformer的因果推断方法，其核心创新在于将因果有向无环图（DAG）直接融入注意力机制，从而准确建模底层因果结构。该方法可灵活估计平均处理效应（ATE）和条件平均处理效应（CATE）。在合成与真实世界数据集上的大量实验表明，该方法在多种因果场景下均优于现有方法。模型的灵活性与鲁棒性使其成为研究者和从业者解决复杂因果推断问题的有力工具。
原文摘要 · Abstract (English)
Causal inference is a critical task across fields such as healthcare, economics, and the social sciences. While recent advances in machine learning, especially those based on the deep-learning architectures, have shown potential in estimating causal effects, existing approaches often fall short in handling complex causal structures and lack adaptability across various causal scenarios. In this paper, we present a novel transformer-based method for causal inference that overcomes these challenges. The core innovation of our model lies in its integration of causal Directed Acyclic Graphs (DAGs) directly into the attention mechanism, enabling it to accurately model the underlying causal structure. This allows for flexible estimation of both average treatment effects (ATE) and conditional average treatment effects (CATE). Extensive experiments on both synthetic and real-world datasets demonstrate that our approach surpasses existing methods in estimating causal effects across a wide range of scenarios. The flexibility and robustness of our model make it a valuable tool for researchers and practitioners tackling complex causal inference problems.
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。