Deep into The Domain Shift: Transfer Learning through Dependence Regularization

TL;DR

This paper introduces a novel domain adaptation method that separately measures and optimizes differences in dependence structures and marginals, improving transferability in applications sensitive to these distinctions.

Contribution

It proposes a new regularization strategy that differentiates and optimizes dependence and marginal differences, enhancing transfer learning effectiveness.

Findings

Significant performance improvements on real-world datasets.

Robustness across various benchmark models.

Enhanced focus on critical domain differences.

Abstract

Classical Domain Adaptation methods acquire transferability by regularizing the overall distributional discrepancies between features in the source domain (labeled) and features in the target domain (unlabeled). They often do not differentiate whether the domain differences come from the marginals or the dependence structures. In many business and financial applications, the labeling function usually has different sensitivities to the changes in the marginals versus changes in the dependence structures. Measuring the overall distributional differences will not be discriminative enough in acquiring transferability. Without the needed structural resolution, the learned transfer is less optimal. This paper proposes a new domain adaptation approach in which one can measure the differences in the internal dependence structure separately from those in the marginals. By optimizing the relative weights among them, the new regularization strategy greatly relaxes the rigidness of the existing approaches. It allows a learning machine to pay special attention to places where the differences matter the most. Experiments on three real-world datasets show that the improvements are quite notable and robust compared to various benchmark domain adaptation models.