DeepMTP: A Python-based deep learning framework for multi-target prediction

Abstract

DeepMTP is a python framework designed to be compatible with the majority of machine learning sub-areas that fall under the umbrella of multi-target prediction (MTP). Multi-target prediction includes problem settings like multi-label classification, multivariate regression, multi-task learning, matrix completion, dyadic prediction, and zero-shot learning. Instead of using separate methodologies for the different problem settings, the proposed framework employs a single flexible two-branch neural network architecture that has been proven to be effective across the majority of MTP problem settings. To our knowledge, this is the first attempt at providing a framework that is compatible with more than two MTP problem settings. The source code of the framework is available at https://github.com/diliadis/DeepMTP and an extension with a graphical user-interface is available at https://github.com/diliadis/DeepMTP_gui.

Keywords

• Multi-target prediction
• Multi-label classification
• Multivariate regression
• Multi-task learning