English

Global Hierarchical Neural Networks using Hierarchical Softmax

Machine Learning 2023-08-03 v1 Computation and Language Machine Learning

Abstract

This paper presents a framework in which hierarchical softmax is used to create a global hierarchical classifier. The approach is applicable for any classification task where there is a natural hierarchy among classes. We show empirical results on four text classification datasets. In all datasets the hierarchical softmax improved on the regular softmax used in a flat classifier in terms of macro-F1 and macro-recall. In three out of four datasets hierarchical softmax achieved a higher micro-accuracy and macro-precision.

Cite

@article{arxiv.2308.01210,
  title  = {Global Hierarchical Neural Networks using Hierarchical Softmax},
  author = {Jetze Schuurmans and Flavius Frasincar},
  journal= {arXiv preprint arXiv:2308.01210},
  year   = {2023}
}

Comments

Submitted to the 35th Symposium on Applied Computing (SAC'20, https://www.sigapp.org/sac/sac2020/), to the Machine Learning and its Applications track (MLA, https://sites.google.com/view/acmsac2020/)

R2 v1 2026-06-28T11:46:32.103Z