Log In Sign Up

Twin Neural Network Regression is a Semi-Supervised Regression Algorithm

by   Sebastian J. Wetzel, et al.

Twin neural network regression (TNNR) is a semi-supervised regression algorithm, it can be trained on unlabelled data points as long as other, labelled anchor data points, are present. TNNR is trained to predict differences between the target values of two different data points rather than the targets themselves. By ensembling predicted differences between the targets of an unseen data point and all training data points, it is possible to obtain a very accurate prediction for the original regression problem. Since any loop of predicted differences should sum to zero, loops can be supplied to the training data, even if the data points themselves within loops are unlabelled. Semi-supervised training improves TNNR performance, which is already state of the art, significantly.


page 11

page 13


How to get the most out of Twinned Regression Methods

Twinned regression methods are designed to solve the dual problem to the...

Twin Neural Network Regression

We introduce twin neural network (TNN) regression. This method predicts ...

Semi-supervised Learning with Explicit Relationship Regularization

In many learning tasks, the structure of the target space of a function ...

Learning Deep Neural Networks under Agnostic Corrupted Supervision

Training deep neural models in the presence of corrupted supervision is ...

Scaling Active Search using Linear Similarity Functions

Active Search has become an increasingly useful tool in information retr...

Prototypal Analysis and Prototypal Regression

Prototypal analysis is introduced to overcome two shortcomings of archet...

Online Active Regression

Active regression considers a linear regression problem where the learne...