Domain-Adversarial Neural Networks | RDL Research Database

Abstract

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).

Keywords

Adversarial systemDomain (mathematical analysis)Artificial neural networkComputer scienceArtificial intelligenceMathematics

Related Publications

Unsupervised Feature Learning via Non-parametric Instance Discrimination

Zhirong Wu , Yuanjun Xiong , Stella X. Yu +1 more

Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether...

2018 3435 citations

Improving neural networks by preventing co-adaptation of feature detectors

Geoffrey E. Hinton , Nitish Srivastava , Alex Krizhevsky +2 more

When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly...

2012 arXiv (Cornell University) 6630 citations

Cascade R-CNN: Delving Into High Quality Object Detection

Zhaowei Cai , Nuno Vasconcelos

In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usua...

2018 6294 citations

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

Sangdoo Yun , Dongyoon Han , Sanghyuk Chun +3 more

Regional dropout strategies have been proposed to enhance performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to atte...

2019 4293 citations

Representation Learning: A Review and New Perspectives

Yoshua Bengio , Aaron Courville , P. M. Durai Raj Vincent

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more...

2013 IEEE Transactions on Pattern Analysis... 12373 citations

Publication Info

Year: 2014
Type: preprint
Citations: 246
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Domain-Adversarial Neural Networks

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

246

OpenAlex

Cite This

APA Style

                            
                                    Hana Ajakan, 
                                
                                    Pascal Germain, 
                                
                                    Hugo Larochelle
                                
                                et al.
                            
                            (2014). 
                            Domain-Adversarial Neural Networks. 
                            arXiv (Cornell University)
                            
                            .
                            https://doi.org/10.48550/arxiv.1412.4446

Identifiers

DOI: 10.48550/arxiv.1412.4446