Neuro-symbolic Learning Yielding Logical Constraints
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909368064147456 |
|---|---|
| author | Li, Zenan Huang, Yunpeng Li, Zhaoyu Yao, Yuan Xu, Jingwei Chen, Taolue Ma, Xiaoxing Lu, Jian |
| author_facet | Li, Zenan Huang, Yunpeng Li, Zhaoyu Yao, Yuan Xu, Jingwei Chen, Taolue Ma, Xiaoxing Lu, Jian |
| contents | Neuro-symbolic systems combine the abilities of neural perception and logical reasoning. However, end-to-end learning of neuro-symbolic systems is still an unsolved challenge. This paper proposes a natural framework that fuses neural network training, symbol grounding, and logical constraint synthesis into a coherent and efficient end-to-end learning process. The capability of this framework comes from the improved interactions between the neural and the symbolic parts of the system in both the training and inference stages. Technically, to bridge the gap between the continuous neural network and the discrete logical constraint, we introduce a difference-of-convex programming technique to relax the logical constraints while maintaining their precision. We also employ cardinality constraints as the language for logical constraint learning and incorporate a trust region method to avoid the degeneracy of logical constraint in learning. Both theoretical analyses and empirical evaluations substantiate the effectiveness of the proposed framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20957 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neuro-symbolic Learning Yielding Logical Constraints Li, Zenan Huang, Yunpeng Li, Zhaoyu Yao, Yuan Xu, Jingwei Chen, Taolue Ma, Xiaoxing Lu, Jian Artificial Intelligence Machine Learning Neuro-symbolic systems combine the abilities of neural perception and logical reasoning. However, end-to-end learning of neuro-symbolic systems is still an unsolved challenge. This paper proposes a natural framework that fuses neural network training, symbol grounding, and logical constraint synthesis into a coherent and efficient end-to-end learning process. The capability of this framework comes from the improved interactions between the neural and the symbolic parts of the system in both the training and inference stages. Technically, to bridge the gap between the continuous neural network and the discrete logical constraint, we introduce a difference-of-convex programming technique to relax the logical constraints while maintaining their precision. We also employ cardinality constraints as the language for logical constraint learning and incorporate a trust region method to avoid the degeneracy of logical constraint in learning. Both theoretical analyses and empirical evaluations substantiate the effectiveness of the proposed framework. |
| title | Neuro-symbolic Learning Yielding Logical Constraints |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.20957 |