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

@article{Lamb2020GraphNN,
  title={Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective},
  author={L. Lamb and A. Garcez and M. Gori and Marcelo O. R. Prates and Pedro H. C. Avelar and Moshe Y. Vardi},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.00330}
}
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… Expand
16 Citations
Computing Graph Neural Networks: A Survey from Algorithms to Accelerators
  • 3
  • PDF
Logic Tensor Networks
  • 2
  • PDF
Symbolic Logic meets Machine Learning: A Brief Survey in Infinite Domains
  • 8
  • PDF
A I ] 1 0 D ec 2 02 0 Neurosymbolic AI : The 3 rd Wave
ERIC: Extracting Relations Inferred from Convolutions
  • PDF
Verifying Strategic Abilities of Neural-symbolic Multi-agent Systems
  • PDF
LOREN: Logic Enhanced Neural Reasoning for Fact Verification
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 95 REFERENCES
The Graph Neural Network Model
  • 1,921
  • PDF
Gated Graph Sequence Neural Networks
  • 1,345
  • PDF
A Survey on The Expressive Power of Graph Neural Networks
  • R. Sato
  • Computer Science, Mathematics
  • ArXiv
  • 2020
  • 22
  • PDF
Neural-Symbolic Learning and Reasoning: Contributions and Challenges
  • 100
  • PDF
Graph Colouring Meets Deep Learning: Effective Graph Neural Network Models for Combinatorial Problems
  • 20
  • PDF
Extracting Relational Explanations From Deep Neural Networks: A Survey From a Neural-Symbolic Perspective
  • 9
Logic programs and connectionist networks
  • 124
  • PDF
Deep Learning for Symbolic Mathematics
  • 72
  • Highly Influential
  • PDF
...
1
2
3
4
5
...