On Target Shift in Adversarial Domain Adaptation
This addresses label shift in domain adaptation, which is crucial for applications like behavioral studies, but it is incremental as it builds on existing adversarial methods.
The paper tackles the problem of label shift in adversarial domain adaptation, where class proportions differ between training and testing domains, and proposes a method called DATS that estimates label proportions and uses domain similarity weighting, achieving strong performance in synthetic and real experiments under large label shift.
Discrepancy between training and testing domains is a fundamental problem in the generalization of machine learning techniques. Recently, several approaches have been proposed to learn domain invariant feature representations through adversarial deep learning. However, label shift, where the percentage of data in each class is different between domains, has received less attention. Label shift naturally arises in many contexts, especially in behavioral studies where the behaviors are freely chosen. In this work, we propose a method called Domain Adversarial nets for Target Shift (DATS) to address label shift while learning a domain invariant representation. This is accomplished by using distribution matching to estimate label proportions in a blind test set. We extend this framework to handle multiple domains by developing a scheme to upweight source domains most similar to the target domain. Empirical results show that this framework performs well under large label shift in synthetic and real experiments, demonstrating the practical importance.