Auto-encoder with Adversarially Regularized Latent Variables for Semi-Supervised Learning

Ryosuke Tachibana, Takashi Matsubara, Kuniaki Uehara
2017 Information Engineering Express  
The amount of accessible raw data is ever-increasing in spite of the difficulty in obtaining a variety of labeled information; this makes semi-supervised learning a topic of practical importance. This paper proposes a novel regularization algorithm of an autoencoding deep neural network for semi-supervised learning. Given an input data, the deep neural network outputs the estimated label, and the remaining information called style. On the basis of the framework of a generative adversarial
more » ... k, the proposed algorithm regularizes the label and the style according to a prior distribution, separating the label explicitly from the style. As a result, the deep neural network is trained to estimate correct labels by using a limitedly labeled dataset. The proposed algorithm achieved accuracy comparable with or superior to that of the existing state-of-the-art semi-supervised algorithms for the benchmark tasks, the MNIST database, and the SVHN dataset.
doi:10.52731/iee.v3.i3.172 fatcat:wex7yrqt2re55eipkr2ydfpkl4