14/09/2020

Effective Version Space Reduction for Convolutional Neural Networks

Jiayu Liu, Ioannis Chiotellis, Rudolph Triebel , Daniel Cremers

Keywords: active learning, deep learning, version space, diameter reduction

Abstract: In active learning, sampling bias could pose a serious inconsistency problem and hinder the algorithm from finding the optimal hypothesis. However, many methods for neural networks are hypothesis space agnostic and do not address this problem. We examine active learning with convolutional neural networks through the principled lens of version space reduction. We identify the connection between two approaches – prior mass reduction and diameter reduction – and propose a new diameter-based querying method – the minimum Gibbs-vote disagreement. By estimating version space diameter and bias, we illustrate how version space of neural networks evolves and examine the realizability assumption. With experiments on MNIST, Fashion-MNIST, SVHN and STL-10 datasets, we demonstrate that diameter reduction methods reduce the version space more effectively and perform better than prior mass reduction and other baselines, and that the Gibbs vote disagreement is on par with the best query method.

 0
 0
 0
 0
This is an embedded video. Talk and the respective paper are published at ECML PKDD 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers