arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1412.4446stat.MLcs.LGcs.NE
收藏

领域对抗神经网络

Domain-Adversarial Neural Networks

Université Laval(拉瓦尔大学);Université de Sherbrooke(舍布鲁克大学)

Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand

摘要:

我们引入了一种新的表示学习算法,适合于域适应的背景下,在训练和测试时的数据来自相似但不同的分布。我们的算法直接受到域自适应理论的启发,这表明为了实现有效的域转移,必须基于无法区分训练(源)和测试(目标)域的数据表示进行预测。我们提出了一个训练目标,实现这一想法的上下文中的神经网络,其隐藏层被训练为预测的分类任务,但不提供信息的域的输入。我们在情感分析分类基准上的实验表明,我们的神经网络域自适应算法比标准神经网络或SVM具有更好的性能,即使是在使用Chen et al.(2012)的最先进的边缘化堆栈去噪自动编码器提取的输入特征上进行训练。

英文摘要:

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).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑