Regularized Transport Weights: a Principled Approach for Active Domain Adaptation

Distribution shift, where there is a mismatch between training and test distributions, is a fundamental challenge in modern machine learning. In this context, we consider the setting of active domain adaptation, where the learner has access to a labeled source dataset $S$, and aims to classify an unlabeled target dataset $T$. The learner is allowed to query the labels of a few points in $T$ to mitigate the distribution shift between $S$ and $T$, as in active learning. We propose a principled, task-agnostic method that jointly selects target queries and reweighs the source and queried examples. Our method tries to effectively use the existing source labels in order to balance coverage of the target distribution while mitigating the variance in the labels. We achieve this by minimizing a natural Regularized Transport Weighting (RTW) objective between the augmented dataset and the target $T$. We provide theoretical guarantees for our method, including a generalization bound and an approximation guarantee for our algorithm. Experiments on standard benchmarks show that our method is competitive with the state-of-the-art methods, and outperforms prior methods on some standard benchmarks– with only a few samples, we are able to train a classifier that significantly improves upon the accuracy achieved on the source dataset alone.