# Simplified Neural Unsupervised Domain Adaptation

## TL;DR

This paper proposes a simplified approach to neural unsupervised domain adaptation by jointly training representation and task learners, challenging the necessity of pivot feature selection methods.

## Contribution

It introduces a joint training framework for UDA that improves performance and analyzes the role of pivot feature selection in existing methods.

## Key findings

- Joint training enhances adaptation performance
- Pivot feature selection may be less critical than previously thought
- Simplified model achieves comparable or better results

## Abstract

Unsupervised domain adaptation (UDA) is the task of modifying a statistical model trained on labeled data from a source domain to achieve better performance on data from a target domain, with access to only unlabeled data in the target domain. Existing state-of-the-art UDA approaches use neural networks to learn representations that can predict the values of subset of important features called "pivot features." In this work, we show that it is possible to improve on these methods by jointly training the representation learner with the task learner, and examine the importance of existing pivot selection methods.