cs.LGcs.LO
HyDI: A hybrid Deep Learning-Inductive Logic Programming ensemble for multi-label classification
📅
👥 2 authors
arXiv:2609.37740v1
Authors
Simon FlügelTill Mossakowski
Abstract
While attaining remarkable results for many applications, Deep Learning models are notoriously difficult to explain. This work introduces HyDI, a hybrid ensemble architecture for hierarchical multi-label classification. It combines a Deep Learning (DL) model with rule-based classifiers generated by Inductive Logic Programming (ILP). For leaf classes of the label hierarchy, the rule-based classifiers replace the DL model, leading to more transparent classification results. HyDI is applied to the Chemical Entities of Biological Interest (ChEBI) ontology, providing ILP-generated rules for 314 classes. For these classes, HyDI can generate global explanations as well as local explanations that combine visual and text-based descriptions.
Paper Information
- arXiv ID:
- 2609.37740v1
- Published:
Related Categories
cs.LGcs.LO