On the limits of dictatorial classification

In the strategyproof classification setting, a set of labeled examples is partitioned among multiple agents. Given the reported labels, an optimal classification mechanism returns a classifier that minimizes the number of mislabeled examples. However, each agent is interested in the accuracy of the returned classifier on its own examples, and may misreport its labels in order to achieve a better classifier, thus contaminating the dataset. The goal is to design strategyproof mechanisms that correctly label as many examples as possible. Previous work has investigated the foregoing setting under limiting assumptions, or with respect to very restricted classes of classifiers. In this paper, we study the strategyproof classification setting with respect to prominent classes of classifiers--boolean conjunctions and linear separators-and without any assumptions on the input. On the negative side, we show that strategyproof mechanisms cannot achieve a constant approximation ratio, by showing ...

• Type: Conference
• Year: 2010
• Where: ATAL
• Authors: Reshef Meir, Ariel D. Procaccia, Jeffrey S. Rosenschein
• Keywords: Approximation Ratio, ATAL 2010, Intelligent Agents, Strategyproof Classification, Strategyproof Mechanisms