Learning Active Learning from Data

Konyushkova, Ksenia; Sznitman, Raphael; Fua, Pascal (2017). Learning Active Learning from Data (In Press). In: Conference on Neural Information Processing Systems (NIPS).

[img] Text
1703.03365.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (632kB)

In this paper, we suggest a novel data-driven approach to active learning (AL). The key idea is to train a regressor that predicts the expected error reduction for a candidate sample in a particular learning state. By formulating the query selection procedure as a regression problem we are not restricted to working with existing AL heuristics; instead, we learn strategies based on experience from previous AL outcomes. We show that a strategy can be learnt either from simple synthetic 2D datasets or from a subset of domain-specific data. Our method yields strategies that work well on real data from a wide range of domains.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

10 Strategic Research Centers > ARTORG Center for Biomedical Engineering Research > ARTORG Center - AI in Medical Imaging Laboratory

UniBE Contributor:

Sznitman, Raphael

Subjects:

600 Technology > 620 Engineering

Language:

English

Submitter:

Raphael Sznitman

Date Deposited:

08 Nov 2017 08:39

Last Modified:

05 Dec 2022 15:07

BORIS DOI:

10.7892/boris.105261

URI:

https://boris.unibe.ch/id/eprint/105261

Actions (login required)

Edit item Edit item
Provide Feedback