Coherent Hierarchical Multi-Label Classification Networks
This addresses hierarchical classification problems in domains like text or image tagging, but it appears incremental as it builds on existing multi-label networks.
The paper tackles hierarchical multi-label classification by proposing C-HMCNN(h), a method that enforces hierarchy constraints to improve prediction coherence and performance, with experimental results showing superior performance compared to state-of-the-art models.
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.