Publication Details

Hyperparameter optimization of two-branch neural networks in multi-target prediction

authored by
Dimitrios Iliadis, Marcel Wever, Bernard De baets, Willem Waegeman
Abstract

As a result of the ever increasing complexity of configuring and fine-tuning machine learning models, the field of automated machine learning (AutoML) has emerged over the past decade. However, software implementations like Auto-WEKA and Auto-sklearn typically focus on classical machine learning (ML) tasks such as classification and regression. Our work can be seen as the first attempt at offering a single AutoML framework for most problem settings that fall under the umbrella of multi-target prediction, which includes popular ML settings such as multi-label classification, multivariate regression, multi-task learning, dyadic prediction, matrix completion, and zero-shot learning. Automated problem selection and model configuration are achieved by extending DeepMTP, a general deep learning framework for MTP problem settings, with popular hyperparameter optimization (HPO) methods. Our extensive benchmarking across different datasets and MTP problem settings identifies cases where specific HPO methods outperform others.

External Organisation(s)
Ghent University
Ludwig-Maximilians-Universität München (LMU)
Type
Article
Journal
Applied soft computing
Volume
165
Pages
111957
ISSN
1568-4946
Publication date
11.2024
Publication status
Published
Peer reviewed
Yes
ASJC Scopus subject areas
Software
Electronic version(s)
https://linkinghub.elsevier.com/retrieve/pii/S1568494624007312 (Access: Unknown)
https://doi.org/10.1016/j.asoc.2024.111957 (Access: Closed)