Mechanism Design for Cost Optimal PAC Learning in the Presence of Strategic Noisy Annotators

TL;DR

This paper addresses PAC learning of binary classifiers from noisy annotators, deriving sample complexity bounds and designing a cost-efficient, incentive-compatible auction mechanism for strategic annotators with private noise rates.

Contribution

It introduces a novel auction mechanism for eliciting true noise rates from strategic annotators, extending PAC learning theory to strategic settings.

Findings

Sample complexity bounds for the complete information case.

A cost optimal auction mechanism for strategic noise rate elicitation.

Mechanism satisfies incentive compatibility.

Abstract

We consider the problem of Probably Approximate Correct (PAC) learning of a binary classifier from noisy labeled examples acquired from multiple annotators (each characterized by a respective classification noise rate). First, we consider the complete information scenario, where the learner knows the noise rates of all the annotators. For this scenario, we derive sample complexity bound for the Minimum Disagreement Algorithm (MDA) on the number of labeled examples to be obtained from each annotator. Next, we consider the incomplete information scenario, where each annotator is strategic and holds the respective noise rate as a private information. For this scenario, we design a cost optimal procurement auction mechanism along the lines of Myerson's optimal auction design framework in a non-trivial manner. This mechanism satisfies incentive compatibility property, thereby facilitating the learner to elicit true noise rates of all the annotators.