Social-Inverse: Inverse Decision-making of Social Contagion Management with Task Migrations

TL;DR

This paper introduces a novel inverse decision-making framework for social contagion management, enabling the use of solutions from one task to solve another without knowing the underlying model, supported by theoretical analysis and empirical validation.

Contribution

The paper proposes a new formal problem of inverse decision-making with task migrations and provides a generic framework with theoretical and empirical validation.

Findings

Successful generalization analysis demonstrating learning performance

Empirical results show effective task migration solutions

First demonstration of cross-task decision-making in social contagion management

Abstract

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.