Visual Perceptual to Conceptual First-Order Rule Learning Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911578310311936 |
|---|---|
| author | Gao, Kun Soldà, Davide Eiter, Thomas Inoue, Katsumi |
| author_facet | Gao, Kun Soldà, Davide Eiter, Thomas Inoue, Katsumi |
| contents | Learning rules plays a crucial role in deep learning, particularly in explainable artificial intelligence and enhancing the reasoning capabilities of large language models. While existing rule learning methods are primarily designed for symbolic data, learning rules from image data without supporting image labels and automatically inventing predicates remains a challenge. In this paper, we tackle these inductive rule learning problems from images with a framework called γILP, which provides a fully differentiable pipeline from image constant substitution to rule structure induction. Extensive experiments demonstrate that γILP achieves strong performance not only on classical symbolic relational datasets but also on relational image data and pure image datasets, such as Kandinsky patterns. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_07897 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Visual Perceptual to Conceptual First-Order Rule Learning Networks Gao, Kun Soldà, Davide Eiter, Thomas Inoue, Katsumi Artificial Intelligence Machine Learning Learning rules plays a crucial role in deep learning, particularly in explainable artificial intelligence and enhancing the reasoning capabilities of large language models. While existing rule learning methods are primarily designed for symbolic data, learning rules from image data without supporting image labels and automatically inventing predicates remains a challenge. In this paper, we tackle these inductive rule learning problems from images with a framework called γILP, which provides a fully differentiable pipeline from image constant substitution to rule structure induction. Extensive experiments demonstrate that γILP achieves strong performance not only on classical symbolic relational datasets but also on relational image data and pure image datasets, such as Kandinsky patterns. |
| title | Visual Perceptual to Conceptual First-Order Rule Learning Networks |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.07897 |