Domain-Adversarial Neural Networks

We introduce a new representation learning algorithm suited to the context of domain adaptation, in which data at training and test time come from similar but different distributions. Our algorithm is directly inspired by theory on domain adaptation suggesting that, for effective domain transfer to...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Ajakan, Hana, Germain, Pascal, Larochelle, Hugo, Laviolette, François, Marchand, Mario
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 09.02.2015
Subjects
Adaptation
Algorithms
Classification
Data mining
Domains
Feature extraction
Machine learning
Neural networks
Noise reduction
Predictions
Representations
Training
Online AccessGet full text

Cover

More Information
Summary:We introduce a new representation learning algorithm suited to the context of domain adaptation, in which data at training and test time come from similar but different distributions. Our algorithm is directly inspired by theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on a data representation that cannot discriminate between the training (source) and test (target) domains. We propose a training objective that implements this idea in the context of a neural network, whose hidden layer is trained to be predictive of the classification task, but uninformative as to the domain of the input. Our experiments on a sentiment analysis classification benchmark, where the target domain data available at training time is unlabeled, show that our neural network for domain adaption algorithm has better performance than either a standard neural network or an SVM, even if trained on input features extracted with the state-of-the-art marginalized stacked denoising autoencoders of Chen et al. (2012).
ISSN:2331-8422