三方众包市场中的发包方-平台博弈机制设计  

Mechanism Design for Requester-Platform Strategies Under the Three-Party Crowdsourcing Market

作　　者：何雨橙 丁尧相 周志华[1] He Yucheng;Ding Yaoxiang;Zhou Zhihua(National Key Laboratory for Novel Software Technology(Nanjing University),Nanjing 210023)

机构地区：[1]计算机软件新技术国家重点实验室(南京大学),南京210023

出　　处：《计算机研究与发展》2022年第11期2507-2519,共13页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(61921006)。

摘　　要：众包(crowdsourcing)通常涉及到目标各不相同的多个参与者.设计有效的众包机制,使得各个参与者在竞争中实现共赢,是众包理论研究中的基本问题之一.当前,众包机制设计通常基于发包方标注者直接进行交互的两方博弈模型.而现实应用中,发包方与标注者之间往往通过平台进行交互,从而构成三方博弈下的众包市场.其中的发包方平台博弈机制设计是过往众包研究中未曾涉及的全新问题.将三方众包市场建模为不完全信息博弈,并证明该博弈问题的Nash均衡可通过在线学习来最小化发包方和平台的累计遗憾而达到.在单发包方情形下,证明经典的EXP3算法对于发包方的最优性,并基于反事实遗憾最小化技术为平台设计了有效策略.同时,将单发包方情形下发包方和平台策略拓展到多发包方情形下并给出理论分析.合成及真实数据集上的实验验证了该方法的有效性.Crowdsourcing usually involves multiple parties of participants with their objectives.One of the fundamental challenges for crowdsourcing is to design effective mechanisms to make all the parties obtain their benefits besides competing.Even though fruitful previous studies have been conducted on this topic,they are usually based on the two-party crowdsourcing models under which one or more requesters and a crowd of workers are involved.However,in real-world applications,the requesters usually interact with the workers through the crowdsourcing platforms,making up the three-party crowdsourcing markets,under which the mechanism design for the requester-platform interaction doesn’t receive previous study.In this work,we model the three-party crowdsourcing market as a game with incomplete information.We show that the Nash Equilibrium of this game can be found via regret minimization with proper online learning strategies.Under the single-requester setting,we show that the classical EXP3 algorithm is optimal for the requester,meanwhile,we propose a stronger strategy for the platform based on the counterfactual regret minimization technique.We also propose effective strategies for both platform and requesters in multiple requesters setting by generalizing the single-requester strategies.The performance of the proposed strategies is verified from experiments with both synthetic and real-world datasets.

关 键 词：众包 博弈理论 机制设计 在线学习 反事实遗憾最小化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]