Semi-supervised representation learning via dual autoencoders for domain adaptation

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.

This paper has been accepted by the journal of KNOWLEDGE-BASED SYSTEMS (KBS) 2019

References in corpus (11)

• Unsupervised Domain Adaptation by Backpropagation
• Conditional Adversarial Domain Adaptation
• Frustratingly Easy Domain Adaptation
• Marginalized Denoising Autoencoders for Domain Adaptation
• Domain Adaptation: Learning Bounds and Algorithms
• Wasserstein Distance Guided Representation Learning for Domain Adaptation
• Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain
• Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
• Domain Adaptation for Ear Recognition Using Deep Convolutional Neural Networks
• A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings
• An Extended Framework for Marginalized Domain Adaptation

Cited by in corpus (1)

• Cross-domain Transfer Learning and State Inference for Soft Robots via a Semi-supervised Sequential Variational Bayes Framework