Research
HyDI: A hybrid Deep Learning-Inductive Logic Programming ensemble for multi-label classification
arXiv:2609.37740v1 Announce Type: new Abstract: While attaining remarkable results for many applications, Deep Learning models are notoriously difficult to explain. This work introduces HyDI, a hybrid
arXiv:2609.37740v1 Announce Type: new 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.
Related
- DeepLog: A Software Framework for Modular Neurosymbolic AI
- Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers
- FL-MHSM: Spatially-adaptive Fusion and Ensemble Learning for Flood-Landslide Multi-Hazard Susceptibility Mapping at Regional Scale
Source: arXiv cs.LG | 2026-09-30