Hybrid model improves multi-label classification with explainable rules
HyDI: A hybrid Deep Learning-Inductive Logic Programming ensemble for multi-label classification
Machine LearningLogic in Computer Science
Summary
Deep learning models are great at classifying complex data, but they can be hard to understand. The authors created a system combining deep learning with rule-based logic to classify items while explaining the decisions clearly. Their system, called HyDI, replaces deep learning with easy-to-understand rules for the most specific labels in a hierarchy. They tested it on a chemical database with many categories, generating explanations that mix visuals and text for clarity.
What this means in practice
- •For bioinformatics teams: Use HyDI to classify chemical entities with clear rule-based explanations, improving trust in automated categorization.
- •For medical data analysts: Apply explainable hybrid classification to label biological data where interpretability of predictions aids decision making.
Tested on one dataset.
Authors
Simon Flügel, Till 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.