Neural networks for feature-extraction in multi-target classification

Abstract

Multi-target learning is a prediction task where each data example is associated with multiple target-variables (outputs) simultaneously. One of the challenges in this research field is related to the high dimensionality of data present in multi-target datasets, and also the high number of target variables having dependencies among themselves. In such scenarios, it is crucial to extract lower-dimensional representations from the original input-space, such that these can be provided as input to other multi-target predictors. In this research, we proposed the use of Auto-Encoders and Restricted Boltzmann Machines as feature extractors in several multi-target classification datasets publicly available. Results were evaluated considering state-of-the-art multi-target classification methods and evaluation measures in the literature. The experiments showed that the neural networks were able to keep the predictive performance even when the extracted features corresponded to a dimension size equivalent to 10% of the original number of features and, in some cases, getting better results than the original datasets.