# Global Hierarchical Neural Networks using Hierarchical Softmax

arXiv: https://arxiv.org/abs/2308.01210 · HTML: https://mlsanity.com/paper/2308.01210/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 2 Aug 2023.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study](https://mlsanity.com/paper/1808.05697/) (2018)
- [A Primer on Neural Network Models for Natural Language Processing](https://mlsanity.com/paper/1510.00726/) (2015)
- [Bayesian Recurrent Neural Networks](https://mlsanity.com/paper/1704.02798/) (2017)
- [BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1711.05715/) (2017)
- [Graph Star Net for Generalized Multi-Task Learning](https://mlsanity.com/paper/1906.12330/) (2019)
- [Neural Attentive Bag-of-Entities Model for Text Classification](https://mlsanity.com/paper/1909.01259/) (2019)

## Built on by (most cited first, 1 of 1)

- [HELM: Hierarchical Encoding for mRNA Language Modeling](https://mlsanity.com/paper/2410.12459/) (2024)

## Abstract (arXiv)

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.