Return of Frustratingly Easy Domain Adaptation

Understand

Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions.

• Such domain shifts, common in practical scenarios, severely damage the performance of conventional machine learning methods.
• Supervised domain adaptation methods have been proposed for the case when the target data have labels, including some that perform very well despite being "frustratingly easy" to implement.
• However, in practice, the target domain is often unlabeled, requiring unsupervised adaptation.