Mind the nuisance: Gaussian process classification using privileged noise
File(s)
Published version
Author(s)
Hernández-Lobato, Daniel
Sharmanska, Viktoriia
Kersting, Kristian
Lampert, Christoph H
Quadrianto, Novi
Type
Conference Paper
Abstract
The learning with privileged information setting has recently attracted a lot
of attention within the machine learning community, as it allows the
integration of additional knowledge into the training process of a classifier,
even when this comes in the form of a data modality that is not available at
test time. Here, we show that privileged information can naturally be treated
as noise in the latent function of a Gaussian Process classifier (GPC). That
is, in contrast to the standard GPC setting, the latent function is not just a
nuisance but a feature: it becomes a natural measure of confidence about the training data by modulating the slope of the GPC sigmoid likelihood function. Extensive experiments on public datasets show that the proposed GPC method using privileged noise, called GPC+, improves over a standard GPC without privileged knowledge, and also over the current state-of-the-art SVM-based method, SVM+. Moreover, we show that advanced neural networks and deep learning methods can be compressed as privileged information.
of attention within the machine learning community, as it allows the
integration of additional knowledge into the training process of a classifier,
even when this comes in the form of a data modality that is not available at
test time. Here, we show that privileged information can naturally be treated
as noise in the latent function of a Gaussian Process classifier (GPC). That
is, in contrast to the standard GPC setting, the latent function is not just a
nuisance but a feature: it becomes a natural measure of confidence about the training data by modulating the slope of the GPC sigmoid likelihood function. Extensive experiments on public datasets show that the proposed GPC method using privileged noise, called GPC+, improves over a standard GPC without privileged knowledge, and also over the current state-of-the-art SVM-based method, SVM+. Moreover, we show that advanced neural networks and deep learning methods can be compressed as privileged information.
Date Issued
2014-12-08
Date Acceptance
2014-12-08
Citation
NIPS'14 Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014
Publisher
Neural Information Processing Systems (NIPS)
Journal / Book Title
NIPS'14 Proceedings of the 27th International Conference on Neural Information Processing Systems
Copyright Statement
© 2014 Neural Information Processing Systems (NIPS)
Identifier
https://papers.nips.cc/paper/5373-mind-the-nuisance-gaussian-process-classification-using-privileged-noise.pdf
Source
Advances in Neural Information Processing Systems (NIPS)
Subjects
Machine Learning
Notes
14 pages with figures
Publication Status
Published
Start Date
2014-12-08
Finish Date
2014-12-13
Coverage Spatial
Montreal, Canada