Compositional Neural Logic Programming
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 3059-3066.
https://doi.org/10.24963/ijcai.2021/421
Keywords
- Machine Learning: Neuro-Symbolic Methods
- Knowledge Representation and Reasoning: Leveraging Knowledge and Learning
Abstract
This paper introduces Compositional Neural Logic Programming (CNLP), a framework that integrates neural networks and logic programming for symbolic and sub-symbolic reasoning. We adopt the idea of compositional neural networks to represent first-order logic predicates and rules. A voting backward-forward chaining algorithm is proposed for inference with both symbolic and sub-symbolic variables in an argument-retrieval style. The framework is highly flexible in that it can be constructed incrementally with new knowledge, and it also supports batch reasoning in certain cases. In the experiments, we demonstrate the advantages of CNLP in discriminative tasks and generative tasks.
@inproceedings{ijcai2021p421,
title = {Compositional Neural Logic Programming},
author = {Tran, Son N.},
booktitle = {Proceedings of the Thirtieth International Joint Conference on
Artificial Intelligence, {IJCAI-21}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Prof. Zhi-Hua Zhou},
pages = {3059--3066},
year = {2021},
month = {8},
note = {Main Track},
doi = {10.24963/ijcai.2021/421},
url = {https://doi.org/10.24963/ijcai.2021/421},
}
TY - CPAPER TI - Compositional Neural Logic Programming AU - Tran, Son N. T2 - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2021 SP - 3059 EP - 3066 DO - 10.24963/ijcai.2021/421 UR - https://doi.org/10.24963/ijcai.2021/421 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
