{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/domain-adversarial-neural-networks","title":"Domain-Adversarial Neural Networks","arxiv_id":"1412.4446","date":"2014-12-15","proceeding":null,"authors":["Hana Ajakan","Pascal Germain","Hugo Larochelle","François Laviolette","Mario Marchand"],"abstract":"We introduce a new representation learning algorithm suited to the context of\ndomain adaptation, in which data at training and test time come from similar\nbut different distributions. Our algorithm is directly inspired by theory on\ndomain adaptation suggesting that, for effective domain transfer to be\nachieved, predictions must be made based on a data representation that cannot\ndiscriminate between the training (source) and test (target) domains. We\npropose a training objective that implements this idea in the context of a\nneural network, whose hidden layer is trained to be predictive of the\nclassification task, but uninformative as to the domain of the input. Our\nexperiments on a sentiment analysis classification benchmark, where the target\ndomain data available at training time is unlabeled, show that our neural\nnetwork for domain adaption algorithm has better performance than either a\nstandard neural network or an SVM, even if trained on input features extracted\nwith the state-of-the-art marginalized stacked denoising autoencoders of Chen\net al. (2012).","url_abs":"http://arxiv.org/abs/1412.4446v2","url_pdf":"http://arxiv.org/pdf/1412.4446v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"domain-adversarial-neural-networks","repo_url":"https://github.com/Kano-Wu/Domain-Adversarial-Neural-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1412.4446","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}