针对特定因果问题设计实验，更高效地获取关键信息。
Goal-Oriented Sequential Bayesian Experimental Design for Causal Learning
- 基于贝叶斯框架，按目标直接优化关键因果量的获益。
- 在有限实验预算下，显著优于现有方法，尤其在复杂机制中。
- 采用可快速决策的神经网络策略，支持实时实验规划。
我们提出 GO-CBED，一种面向目标的序贯贝叶斯因果实验设计框架。与传统方法不同，它不追求完整因果模型推断，而是直接最大化用户指定因果量上的期望信息增益（EIG），实现更精准高效的实验设计。该框架兼具非贪心性（优化整个干预序列）和目标导向性（仅关注与因果查询相关的模型部分）。为应对精确 EIG 计算不可行的问题，我们引入变分下界估计器，通过基于 Transformer 的策略网络与基于归一化流的变分后验联合优化，构建可快速推理的策略网络。实验表明，GO-CBED 在多种任务中持续超越基线方法，包括合成结构因果模型和半合成基因调控网络，尤其在实验预算有限、因果机制复杂的情况下表现突出。结果凸显了将实验设计目标与具体研究问题对齐，以及前瞻性序贯规划的价值。
原文摘要 · Abstract (English)
We present GO-CBED, a goal-oriented Bayesian framework for sequential causal experimental design. Unlike conventional approaches that select interventions aimed at inferring the full causal model, GO-CBED directly maximizes the expected information gain (EIG) on user-specified causal quantities of interest, enabling more targeted and efficient experimentation. The framework is both non-myopic, optimizing over entire intervention sequences, and goal-oriented, targeting only model aspects relevant to the causal query. To address the intractability of exact EIG computation, we introduce a variational lower bound estimator, optimized jointly through a transformer-based policy network and normalizing flow-based variational posteriors. The resulting policy enables real-time decision-making via an amortized network. We demonstrate that GO-CBED consistently outperforms existing baselines across various causal reasoning and discovery tasks-including synthetic structural causal models and semi-synthetic gene regulatory networks-particularly in settings with limited experimental budgets and complex causal mechanisms. Our results highlight the benefits of aligning experimental design objectives with specific research goals and of forward-looking sequential planning.
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。