Algorithms for strategyproof classification

Reshef Meir*, Ariel D. Procaccia, Jeffrey S. Rosenschein

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

54 Scopus citations


The strategyproof classification problem deals with a setting where a decision maker must classify a set of input points with binary labels, while minimizing the expected error. The labels of the input points are reported by self-interested agents, who might lie in order to obtain a classifier that more closely matches their own labels, thereby creating a bias in the data; this motivates the design of truthful mechanisms that discourage false reports. In this paper we give strategyproof mechanisms for the classification problem in two restricted settings: (i) there are only two classifiers, and (ii) all agents are interested in a shared set of input points. We show that these plausible assumptions lead to strong positive results. In particular, we demonstrate that variations of a random dictator mechanism, that are truthful, can guarantee approximately optimal outcomes with respect to any family of classifiers. Moreover, these results are tight in the sense that they match the best possible approximation ratio that can be guaranteed by any truthful mechanism. We further show how our mechanisms can be used for learning classifiers from sampled data, and provide PAC-style generalization bounds on their expected error. Interestingly, our results can be applied to problems in the context of various fields beyond classification, including facility location and judgment aggregation.

Original languageAmerican English
Pages (from-to)123-156
Number of pages34
JournalArtificial Intelligence
StatePublished - Jul 2012

Bibliographical note

Funding Information:
This work was partially supported by Israel Science Foundation grant #898/05, the Israel Ministry of Science and Technology grant #3-6797, and the Google Inter-University Center for Electronic Markets and Auctions. The authors thank Omri Abend, Shaull Almagor, Assaf Michaely and Ilan Nehama for their enlightening comments on drafts of this paper.


  • Approximation
  • Classification
  • Game theory
  • Mechanism design


Dive into the research topics of 'Algorithms for strategyproof classification'. Together they form a unique fingerprint.

Cite this