# HyDI: A hybrid Deep Learning-Inductive Logic Programming ensemble for multi-label classification

arXiv: https://arxiv.org/abs/2609.37740 · HTML: https://mlsanity.com/paper/2609.37740/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 10 of 10)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Learning programs by learning from failures](https://mlsanity.com/paper/2005.02259/) (2020)
- [The ILASP system for Inductive Learning of Answer Set Programs](https://mlsanity.com/paper/2005.00904/) (2020)
- [Enriching Visual with Verbal Explanations for Relational Concepts -- Combining LIME with Aleph](https://mlsanity.com/paper/1910.01837/) (2019)
- [Expressive Explanations of DNNs by Combining Concept Analysis with ILP](https://mlsanity.com/paper/2105.07371/) (2021)
- [A System for Explainable Answer Set Programming](https://mlsanity.com/paper/2009.10242/) (2020)
- [A Critical Review of Inductive Logic Programming Techniques for Explainable AI](https://mlsanity.com/paper/2112.15319/) (2021)
- [Learning logic programs by discovering where not to search](https://mlsanity.com/paper/2202.09806/) (2022)
- [Chemical classification program synthesis using generative artificial intelligence](https://mlsanity.com/paper/2505.18470/) (2025)
- [ChemLog: Making MSOL Viable for Ontological Classification and Learning](https://mlsanity.com/paper/2507.13987/) (2025)

## Abstract (arXiv)

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.