Simplified Neural Unsupervised Domain Adaptation
This work addresses domain adaptation for machine learning models, but appears incremental as it builds on existing pivot feature methods.
The paper tackles unsupervised domain adaptation by proposing a method that jointly trains representation and task learners, improving on existing state-of-the-art approaches that rely on pivot features.
Unsupervised domain adaptation (UDA) is the task of modifying a statistical model trained on labeled data from a source domain to achieve better performance on data from a target domain, with access to only unlabeled data in the target domain. Existing state-of-the-art UDA approaches use neural networks to learn representations that can predict the values of subset of important features called "pivot features." In this work, we show that it is possible to improve on these methods by jointly training the representation learner with the task learner, and examine the importance of existing pivot selection methods.