Coherent Hierarchical Multi-Label Classification Networks

Abstract

Hierarchical multi-label classification (HMC) is a challenging classification task extending standard multi-label classification problems by imposing a hierarchy constraint on the classes. In this paper, we propose C-HMCNN(h), a novel approach for HMC problems, which, given a network h for the underlying multi-label classification problem, exploits the hierarchy information in order to produce predictions coherent with the constraint and improve performance. We conduct an extensive experimental analysis showing the superior performance of C-HMCNN(h) when compared to state-of-the-art models.

PDF NeurIPS Semantic Scholar

Cite

Text

Giunchiglia and Lukasiewicz. "Coherent Hierarchical Multi-Label Classification Networks." Neural Information Processing Systems, 2020.

Markdown

[Giunchiglia and Lukasiewicz. "Coherent Hierarchical Multi-Label Classification Networks." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/giunchiglia2020neurips-coherent/)

BibTeX

@inproceedings{giunchiglia2020neurips-coherent,
  title     = {{Coherent Hierarchical Multi-Label Classification Networks}},
  author    = {Giunchiglia, Eleonora and Lukasiewicz, Thomas},
  booktitle = {Neural Information Processing Systems},
  year      = {2020},
  url       = {https://mlanthology.org/neurips/2020/giunchiglia2020neurips-coherent/}
}