---
title: "Compositional Neural Logic Programming"
authors:
  - "Son N. Tran"
doi: "10.24963/ijcai.2021/421"
url: "https://ijcai.org/proceedings/2021/421"
pdf: "https://ijcai.org/proceedings/2021/0421.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "3059-3066"
track: "Main Track"
keywords:
  - "Machine Learning: Neuro-Symbolic Methods"
  - "Knowledge Representation and Reasoning: Leveraging Knowledge and Learning"
---

# Compositional Neural Logic Programming

Son N. Tran

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 3059-3066. DOI: [10.24963/ijcai.2021/421](https://doi.org/10.24963/ijcai.2021/421)

## 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.