aiqbench analysis
This research presents HyDI, a hybrid ensemble architecture that integrates Deep Learning with Inductive Logic Programming to enhance explainability in hierarchical multi-label classification tasks. By substituting deep learning models with rule-based classifiers at the leaf nodes of a hierarchy, the system generates both global and local explanations for chemical entity classifications within the ChEBI ontology. The approach directly addresses the interpretability gap in black-box models by combining neural network performance with transparent, logic-derived rules.
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 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.
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.
Machine Learning (cs.LG); Logic in Computer Science (cs.LO)
arXiv:2609.37740 [cs.LG]
(or arXiv:2609.37740v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.37740 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 199 words
