Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 1.55 MB
Add to list
  1. Search results
  2. Multi-target prediction for dummies u...

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

Dimitrios Iliadis (UGent) , Bernard De Baets (UGent) and Willem Waegeman (UGent)
(2022) MACHINE LEARNING. 111(2). p.651-684
Author
Organization
Project
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.
Keywords
Multi-target prediction, Multi-label classification, Multivariate regression, Matrix completion, Multi-task learning, Dyadic prediction, MULTI-LABEL CLASSIFICATION, SUPPORT VECTOR REGRESSION

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.55 MB

Citation

Please use this url to cite or link to this publication:

MLA
Iliadis, Dimitrios, et al. “Multi-Target Prediction for Dummies Using Two-Branch Neural Networks.” MACHINE LEARNING, vol. 111, no. 2, 2022, pp. 651–84, doi:10.1007/s10994-021-06104-5.
APA
Iliadis, D., De Baets, B., & Waegeman, W. (2022). Multi-target prediction for dummies using two-branch neural networks. MACHINE LEARNING, 111(2), 651–684. https://doi.org/10.1007/s10994-021-06104-5
Chicago author-date
Iliadis, Dimitrios, Bernard De Baets, and Willem Waegeman. 2022. “Multi-Target Prediction for Dummies Using Two-Branch Neural Networks.” MACHINE LEARNING 111 (2): 651–84. https://doi.org/10.1007/s10994-021-06104-5.
Chicago author-date (all authors)
Iliadis, Dimitrios, Bernard De Baets, and Willem Waegeman. 2022. “Multi-Target Prediction for Dummies Using Two-Branch Neural Networks.” MACHINE LEARNING 111 (2): 651–684. doi:10.1007/s10994-021-06104-5.
Vancouver
1.
Iliadis D, De Baets B, Waegeman W. Multi-target prediction for dummies using two-branch neural networks. MACHINE LEARNING. 2022;111(2):651–84.
IEEE
[1]
D. Iliadis, B. De Baets, and W. Waegeman, “Multi-target prediction for dummies using two-branch neural networks,” MACHINE LEARNING, vol. 111, no. 2, pp. 651–684, 2022.
@article{8750435,
  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.}},
  author       = {{Iliadis, Dimitrios and De Baets, Bernard and Waegeman, Willem}},
  issn         = {{0885-6125}},
  journal      = {{MACHINE LEARNING}},
  keywords     = {{Multi-target prediction,Multi-label classification,Multivariate regression,Matrix completion,Multi-task learning,Dyadic prediction,MULTI-LABEL CLASSIFICATION,SUPPORT VECTOR REGRESSION}},
  language     = {{eng}},
  number       = {{2}},
  pages        = {{651--684}},
  title        = {{Multi-target prediction for dummies using two-branch neural networks}},
  url          = {{http://doi.org/10.1007/s10994-021-06104-5}},
  volume       = {{111}},
  year         = {{2022}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: