Search Improves Label for Active Learning

02/23/2016 ∙ by Alina Beygelzimer, et al. ∙ 0 ∙ share

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.

READ FULL TEXT

SoQal: Selective Oracle Questioning in Active Learning

Large sets of unlabelled data within the healthcare domain remain underu...
04/22/2020 ∙ by Dani Kiyasseh, et al. ∙ 0 ∙ share

read it
The Label Complexity of Active Learning from Observational Data

Counterfactual learning from observational data involves learning a clas...
05/29/2019 ∙ by Songbai Yan, et al. ∙ 0 ∙ share

read it
Active Learning under Label Shift

Distribution shift poses a challenge for active data collection in the r...
07/16/2020 ∙ by Eric Zhao, et al. ∙ 18 ∙ share

read it
Exemplar Guided Active Learning

We consider the problem of wisely using a limited budget to label a smal...
11/02/2020 ∙ by Jason Hartford, et al. ∙ 8 ∙ share

read it
Nonmyopic Multifidelity Active Search

Active search is a learning paradigm where we seek to identify as many m...
06/11/2021 ∙ by Quan Nguyen, et al. ∙ 0 ∙ share

read it
The Power of Comparisons for Actively Learning Linear Classifiers

In the world of big data, large but costly to label datasets dominate ma...
07/08/2019 ∙ by Max Hopkins, et al. ∙ 4 ∙ share

read it
Computer-Assisted Fraud Detection, From Active Learning to Reward Maximization

The automatic detection of frauds in banking transactions has been recen...
11/20/2018 ∙ by Christelle Marfaing, et al. ∙ 0 ∙ share

read it

Search Improves Label for Active Learning

Authors

SoQal: Selective Oracle Questioning in Active Learning

The Label Complexity of Active Learning from Observational Data

Active Learning under Label Shift

Exemplar Guided Active Learning

Nonmyopic Multifidelity Active Search

The Power of Comparisons for Actively Learning Linear Classifiers

Computer-Assisted Fraud Detection, From Active Learning to Reward Maximization

This week in AI