Adversarial Weighting for Domain Adaptation in Regression

TL;DR

This paper introduces an adversarial weighting method for supervised regression domain adaptation under covariate shift, enabling effective reweighting of source instances during training to improve target domain performance.

Contribution

It proposes a novel adversarial approach that jointly learns source instance weights and the regression task, based on a discrepancy distance for domain difference.

Findings

Effective on public regression domain adaptation datasets

Reproducible experiments demonstrate improved performance

Novel formulation of discrepancy-based optimization

Abstract

We present a novel instance-based approach to handle regression tasks in the context of supervised domain adaptation under an assumption of covariate shift. The approach developed in this paper is based on the assumption that the task on the target domain can be efficiently learned by adequately reweighting the source instances during training phase. We introduce a novel formulation of the optimization objective for domain adaptation which relies on a discrepancy distance characterizing the difference between domains according to a specific task and a class of hypotheses. To solve this problem, we develop an adversarial network algorithm which learns both the source weighting scheme and the task in one feed-forward gradient descent. We provide numerical evidence of the relevance of the method on public data sets for regression domain adaptation through reproducible experiments.