Abstract
Neural-symbolic computing has now become the subject of interest of both academic and industry research laboratories.
Graph Neural Networks (GNNs) have been widely used in relational and symbolic domains, with widespread application of GNNs in combinatorial optimization, constraint satisfaction, relational reasoning and other scientific domains.
The need for improved explainability, interpretability and trust of AI systems in general demands principled methodologies, as suggested by neural-symbolic computing.
In this paper, we review the state-of-the-art on the use of GNNs as a model of neural-symbolic computing. This includes the application of GNNs in several domains as well as their relationship to current developments in neural-symbolic computing.
Keywords
- Safe, Explainable, and Trustworthy AI: general
- Knowledge Representation and Reasoning: general
- Machine Learning: general
- Constraints and Satisfiability: general
