Social-Inverse: Inverse Decision-making of Social Contagion Management with Task Migrations
Social-Inverse: Inverse Decision-making of Social Contagion Management with Task Migrations
复制标题
DOI：
10.48550/arxiv.2209.10493
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
G. Tong
中科院分区：
文献类型：
--
作者：
G. Tong
考虑到两个决策任务$A$和$B$，每个任务都希望对给定的\textit{查询}$X$计算一个有效的\textit{决策}$Y$，{我们是否可以}{在不知道潜在决策模型的情况下，使用}{$A$}{的查询-决策对}{$(X, Y)$}{来求解任务}{$B$}{ ？}这类问题被称为\textit{带有任务迁移的逆决策}（inverse decision- decision with task migration），其有趣之处在于，现实世界应用程序的复杂性和随机性常常使代理无法完全了解底层系统。在本文中，我们用正式公式介绍了这样一个新问题，并提出了一个解决社会传染管理决策任务的通用框架。在理论方面，我们提出了一个泛化分析来证明我们框架的学习性能。在实证研究中，我们执行健全检查，并将所提出的方法与其他可能的基于学习和基于图的方法进行比较。我们已经获得了很有希望的实验结果，首次证实了利用与另一个决策任务相关的解来解决一个决策任务是可能的。
Considering two decision-making tasks $A$ and $B$, each of which wishes to compute an effective \textit{decision} $Y$ for a given \textit{query} $X$, {can we solve task $B$ by using query-decision pairs $(X, Y)$ of $A$ without knowing the latent decision-making model?} Such problems, called \textit{inverse decision-making with task migrations}, are of interest in that the complex and stochastic nature of real-world applications often prevents the agent from completely knowing the underlying system. In this paper, we introduce such a new problem with formal formulations and present a generic framework for addressing decision-making tasks in social contagion management. On the theory side, we present a generalization analysis for justifying the learning performance of our framework. In empirical studies, we perform a sanity check and compare the presented method with other possible learning-based and graph-based methods. We have acquired promising experimental results, confirming for the first time that it is possible to solve one decision-making task by using the solutions associated with another one.