Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance
This work addresses the challenge of expensive or impossible data acquisition for regression tasks, offering a semi-supervised solution that outperforms existing methods.
The paper tackles the problem of training deep learning models with limited labeled data by introducing semi-supervised deep kernel learning (SSDKL), which improves regression performance on real-world tasks by leveraging unlabeled data to minimize predictive variance.
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.