Multi-target prediction for dummies using two-branch neural networks
This work addresses the high entrance barrier for machine learning practitioners by providing a unified approach to multi-target prediction, though it is incremental as it builds on existing neural network techniques.
The authors tackled the fragmentation of multi-target prediction (MTP) tasks by developing a generic deep learning methodology with a flexible neural network architecture, which achieved competitive performance across various domains compared to specialized methods.
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.