ALPS: Active Learning via Perturbations

by   Dani Kiyasseh, et al.

Small, labelled datasets in the presence of larger, unlabelled datasets pose challenges to data-hungry deep learning algorithms. Such scenarios are prevalent in healthcare where labelling is expensive, time-consuming, and requires expert medical professionals. To tackle this challenge, we propose a family of active learning methodologies and acquisition functions dependent upon input and parameter perturbations which we call Active Learning via Perturbations (ALPS). We test our methods on six diverse time-series and image datasets and illustrate their benefit in the presence and absence of an oracle. We also show that acquisition functions that incorporate temporal information have the potential to predict the ability of networks to generalize.


SoQal: Selective Oracle Questioning in Active Learning

Large sets of unlabelled data within the healthcare domain remain underu...

Active Learning with Expert Advice

Conventional learning with expert advice methods assumes a learner is al...

How useful is Active Learning for Image-based Plant Phenotyping?

Deep learning models have been successfully deployed for a diverse array...

An overview of active learning methods for insurance with fairness appreciation

This paper addresses and solves some challenges in the adoption of machi...

On the Evaluation Criterions for the Active Learning Processes

In many data mining applications collection of sufficiently large datase...

Investigating the Effectiveness of Word-Embedding Based Active Learning for Labelling Text Datasets

Manually labelling large collections of text data is a time-consuming, e...

Please sign up or login with your details

Forgot password? Click here to reset