Depth Uncertainty Networks for Active Learning

12/13/2021
by   Chelsea Murray, et al.
0

In active learning, the size and complexity of the training dataset changes over time. Simple models that are well specified by the amount of data available at the start of active learning might suffer from bias as more points are actively sampled. Flexible models that might be well suited to the full dataset can suffer from overfitting towards the start of active learning. We tackle this problem using Depth Uncertainty Networks (DUNs), a BNN variant in which the depth of the network, and thus its complexity, is inferred. We find that DUNs outperform other BNN variants on several active learning tasks. Importantly, we show that on the tasks in which DUNs perform best they present notably less overfitting than baselines.

READ FULL TEXT

page 2

page 10

page 17

research
12/13/2021

Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not

Farquhar et al. [2021] show that correcting for active learning bias wit...
research
11/08/2019

Char-RNN and Active Learning for Hashtag Segmentation

We explore the abilities of character recurrent neural network (char-RNN...
research
07/31/2017

Interpretable Active Learning

Active learning has long been a topic of study in machine learning. Howe...
research
09/22/2020

Model-Centric and Data-Centric Aspects of Active Learning for Neural Network Models

We study different data-centric and model-centric aspects of active lear...
research
01/27/2021

On Statistical Bias In Active Learning: How and When To Fix It

Active learning is a powerful tool when labelling data is expensive, but...
research
07/12/2018

How transferable are the datasets collected by active learners?

Active learning is a widely-used training strategy for maximizing predic...
research
11/29/2018

The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning

One of the main challenges of deep learning tools is their inability to ...

Please sign up or login with your details

Forgot password? Click here to reset