Learning Disentangled Semantic Representation for Domain Adaptation

12/22/2020
by   Ruichu Cai, et al.
0

Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space with entangling domain information and semantic information. Different from previous efforts on the entangled feature space, we aim to extract the domain invariant semantic information in the latent disentangled semantic representation (DSR) of the data. In DSR, we assume the data generation process is controlled by two independent sets of variables, i.e., the semantic latent variables and the domain latent variables. Under the above assumption, we employ a variational auto-encoder to reconstruct the semantic latent variables and domain latent variables behind the data. We further devise a dual adversarial network to disentangle these two sets of reconstructed latent variables. The disentangled semantic latent variables are finally adapted across the domains. Experimental studies testify that our model yields state-of-the-art performance on several domain adaptation benchmark datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/14/2021

Graph Domain Adaptation: A Generative View

Recent years have witnessed tremendous interest in deep learning on grap...
09/28/2018

Adversarial Domain Adaptation for Stable Brain-Machine Interfaces

Brain-Machine Interfaces (BMIs) have recently emerged as a clinically vi...
12/22/2020

Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition

Named entity recognition (NER) for identifying proper nouns in unstructu...
12/24/2020

Disentangling semantics in language through VAEs and a certain architectural choice

We present an unsupervised method to obtain disentangled representations...
09/27/2018

Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning

Revealing latent structure in data is an active field of research, havin...
05/18/2017

Spatial Variational Auto-Encoding via Matrix-Variate Normal Distributions

The key idea of variational auto-encoders (VAEs) resembles that of tradi...