# Semi-supervised representation learning via dual autoencoders for domain adaptation

## TL;DR

This paper introduces SSRLDA, a semi-supervised domain adaptation method using dual autoencoders to capture both global and local features, leveraging label information for improved performance.

## Contribution

It proposes a novel dual autoencoder framework that simultaneously learns global and local features for domain adaptation, incorporating label information to enhance feature representation.

## Key findings

- Outperforms several state-of-the-art methods in domain adaptation tasks.
- Effectively captures local relationships between instances across domains.
- Utilizes label information to optimize feature learning.

## Abstract

Domain adaptation aims to exploit the knowledge in source domain to promote the learning tasks in target domain, which plays a critical role in real-world applications. Recently, lots of deep learning approaches based on autoencoders have achieved a significance performance in domain adaptation. However, most existing methods focus on minimizing the distribution divergence by putting the source and target data together to learn global feature representations, while they do not consider the local relationship between instances in the same category from different domains. To address this problem, we propose a novel Semi-Supervised Representation Learning framework via Dual Autoencoders for domain adaptation, named SSRLDA. More specifically, we extract richer feature representations by learning the global and local feature representations simultaneously using two novel autoencoders, which are referred to as marginalized denoising autoencoder with adaptation distribution (MDAad) and multi-class marginalized denoising autoencoder (MMDA) respectively. Meanwhile, we make full use of label information to optimize feature representations. Experimental results show that our proposed approach outperforms several state-of-the-art baseline methods.