Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance

Abstract

Large amounts of labeled data are typically required to train deep learning models. For many real-world problems, however, acquiring additional data can be expensive or even impossible. We present semi-supervised deep kernel learning (SSDKL), a semi-supervised regression model based on minimizing predictive variance in the posterior regularization framework. SSDKL combines the hierarchical representation learning of neural networks with the probabilistic modeling capabilities of Gaussian processes. By leveraging unlabeled data, we show improvements on a diverse set of real-world regression tasks over supervised deep kernel learning and semi-supervised methods such as VAT and mean teacher adapted for regression. * denotes equal contribution Preprint. Work in progress.

Twin neural network regression is a semi-supervised regression algorithm

“…Semi-supervised regression was a research area before neural networks became popular in 2012 [3]. However, only very few research articles have since included neural networks as part of their proposed semi-supervised regression pipelines, mostly combined with other machine learning algorithms [4,5]. While neural networks are not always the optimal choice, their performance ceiling is much higher due to the universal approximation theorem [6,7], the incorporation of feature extraction into the learning problem, and the efficient training through gradient descent and backpropagation.…”

Twin Neural Network Regression is a Semi-Supervised Regression Algorithm

“…Semi-supervised regression was a research area before neural networks became popular in 2012 [13]. However, only very few research articles have since included neural networks as part of their proposed semi-supervised regression pipelines, mostly combined with other machine learning algorithms [11,14]. While neural networks are not always the optimal choice, their performance ceiling is much higher due to the universal approximation theorem [8,10], the incorporation of feature extraction into the learning problem, and the efficient training through gradient descent and backpropagation.…”