Active Learning with Label Proportions

Active Learning (AL) refers to the setting where the learner has the ability to perform queries to an oracle to acquire the true label of an instance or, sometimes, a set of instances. Even though Active Learning has been studied extensively, the setting is usually restricted to assume that the orac...

Full description

Saved in:

Bibliographic Details
Published in:	ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 3097 - 3101
Main Authors:	Poyiadzis, Rafael, Santos-Rodriguez, Raul, Twomey, Niall
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-05-2019
Subjects:	Active learning Gold Intelligent systems label propagation label proportions Labeling Noise measurement Task analysis Training Uncertainty
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Active Learning (AL) refers to the setting where the learner has the ability to perform queries to an oracle to acquire the true label of an instance or, sometimes, a set of instances. Even though Active Learning has been studied extensively, the setting is usually restricted to assume that the oracle is trustworthy and will provide the actual label. We argue that, while common, this approach can be made more flexible to account for different forms of supervision. In this paper, we propose a new framework that allows the algorithm to request the label for a bag of samples at a time. Although this label will come in the form of proportions of class labels in the bags and therefore encode less information, we demonstrate that we can still learn effectively.
ISSN:	2379-190X
DOI:	10.1109/ICASSP.2019.8682748