NeurIPS 2020poster144 citations

Coherent Hierarchical Multi-Label Classification Networks

Eleonora Giunchiglia, Thomas Lukasiewicz

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.

BibTeX
@inproceedings{NEURIPS2020_6dd4e10e,
 author = {Giunchiglia, Eleonora and Lukasiewicz, Thomas},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
 pages = {9662--9673},
 publisher = {Curran Associates, Inc.},
 title = {Coherent Hierarchical Multi-Label Classification Networks},
 url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/6dd4e10e3296fa63738371ec0d5df818-Paper.pdf},
 volume = {33},
 year = {2020}
}
Coherent Hierarchical Multi-Label Classification Networks · NeurIPS 2020