Search Improves Label for Active Learning

TL;DR

This paper explores a novel active learning approach that combines traditional labeling with a search-based oracle, leading to exponential improvements in learning efficiency in certain problems.

Contribution

It introduces a new active learning framework utilizing both Label and Search oracles, demonstrating significant problem-dependent advantages over standard methods.

Findings

Search oracle enhances active learning effectiveness.

Combining Search with Label yields exponential improvements.

The approach is practical and applicable in real-world scenarios.

Abstract

We investigate active learning with access to two distinct oracles: Label (which is standard) and Search (which is not). The Search oracle models the situation where a human searches a database to seed or counterexample an existing solution. Search is stronger than Label while being natural to implement in many situations. We show that an algorithm using both oracles can provide exponentially large problem-dependent improvements over Label alone.