Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective

by   Luis Lamb, et al.
City, University of London
Università di Siena
Rice University

Neural-symbolic computing has now become the subject of interest of both academic and industry research laboratories. Graph Neural Networks (GNN) 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 its relationship to current developments in neural-symbolic computing.


page 1

page 2

page 3

page 4


Neurosymbolic AI: The 3rd Wave

Current advances in Artificial Intelligence (AI) and Machine Learning (M...

Combinatorial optimization and reasoning with graph neural networks

Combinatorial optimization is a well-established area in operations rese...

Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks

We present a novel deep reinforcement learning framework for solving rel...

Combining Sub-Symbolic and Symbolic Methods for Explainability

Similarly to other connectionist models, Graph Neural Networks (GNNs) la...

Graph Colouring Meets Deep Learning: Effective Graph Neural Network Models for Combinatorial Problems

Deep learning has consistently defied state-of-the-art techniques in man...

Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits

It has been recently shown that general policies for many classical plan...

Please sign up or login with your details

Forgot password? Click here to reset