In collaborative active learning, where multiple agents try to learn labels from a common hypothesis, we introduce an innovative framework for incentivized collaboration. Here, rational agents aim to obtain labels for their data sets while keeping label complexity at a minimum. We focus on designing (strict) individually rational (IR) collaboration protocols, ensuring that agents cannot reduce their expected label complexity by acting individually. We first show that given any optimal active learning algorithm, the collaboration protocol that runs the algorithm as is over the entire data is already IR. However, computing the optimal algorithm is NP-hard. We therefore provide collaboration protocols that achieve (strict) IR and are comparable with the best known tractable approximation algorithm in terms of label complexity.

翻译：在协作式主动学习中，当多个智能体试图从共享假设中学习标签时，我们提出了一种激励协作的创新框架。在此框架下，理性智能体的目标是在最小化标签复杂度的同时为其数据集获取标签。我们专注于设计（严格）个体理性协作协议，确保智能体通过单独行动无法降低其预期标签复杂度。首先，我们证明给定任何最优主动学习算法，将整个数据直接应用该算法的协作协议已满足个体理性条件。然而，计算最优算法是NP难的。因此，我们提供了既能实现（严格）个体理性，又在标签复杂度方面与已知最佳易处理近似算法相当的协作协议。