Network interference has garnered significant interest in the field of causal inference. It reflects diverse sociological behaviors, wherein the treatment assigned to one individual within a network may influence the outcome of other individuals, such as their neighbors. To estimate the causal effect, one classical way is to randomly assign experimental candidates into different groups and compare their differences. However, in the context of sequential experiments, such treatment assignment may result in a large regret. In this paper, we develop a unified interference-based online experimental design framework. Compared to existing literature, we expand the definition of arm space by leveraging the statistical concept of exposure mapping. Importantly, we establish the Pareto-optimal trade-off between the estimation accuracy and regret with respect to both time period and arm space, which remains superior to the baseline even in the absence of network interference. We further propose an algorithmic implementation and model generalization.

翻译：网络干扰在因果推断领域引起了广泛关注。它反映了多样化的社会行为，即网络中某个个体被分配的处理可能会影响其他个体（例如其邻居）的结果。为估计因果效应，一种经典方法是将实验对象随机分配到不同组别并比较其差异。然而，在序贯实验的背景下，这种处理分配可能导致较大的遗憾。本文提出了一个基于网络干扰的统一在线实验设计框架。与现有文献相比，我们通过利用暴露映射的统计概念扩展了臂空间的定义。重要的是，我们建立了关于时间周期和臂空间的估计精度与遗憾之间的帕累托最优权衡，即使在不存在网络干扰的情况下，该权衡仍优于基线。我们进一步提出了算法实现与模型泛化方案。