Multi-target prediction for dummies using two-branch neural networks

TL;DR

This paper introduces a flexible deep learning framework using two-branch neural networks designed to simplify and unify multi-target prediction tasks across various domains, making advanced methods more accessible.

Contribution

The authors propose a generic multi-branch neural network architecture with a user-friendly configuration process, unifying multiple MTP tasks into a single adaptable model.

Findings

Competitive performance across diverse MTP domains

Simplifies the application of multi-target prediction methods

Reduces the need for domain-specific expertise

Abstract

Multi-target prediction (MTP) serves as an umbrella term for machine learning tasks that concern the simultaneous prediction of multiple target variables. Classical instantiations are multi-label classification, multivariate regression, multi-task learning, dyadic prediction, zero-shot learning, network inference, and matrix completion. Despite the significant similarities, all these domains have evolved separately into distinct research areas over the last two decades. This led to the development of a plethora of highly-engineered methods, and created a substantially-high entrance barrier for machine learning practitioners that are not experts in the field. In this work we present a generic deep learning methodology that can be used for a wide range of multi-target prediction problems. We introduce a flexible multi-branch neural network architecture, partially configured via a questionnaire that helps end-users to select a suitable MTP problem setting for their needs. Experimental results for a wide range of domains illustrate that the proposed methodology manifests a competitive performance compared to methods from specific MTP domains.