Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective
arXiv:2003.00330
Abstract
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.
Updated version, draft of accepted IJCAI2020 Survey Paper
References in corpus (5)
- The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
- Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge
- A Survey on The Expressive Power of Graph Neural Networks
- G2SAT: Learning to Generate SAT Formulas
- The Use of Deep Learning for Symbolic Integration: A Review of (Lample and Charton, 2019)
Cited by in corpus (17)
- ChatGPT for Shaping the Future of Dentistry: The Potential of Multi-Modal Large Language Model
- Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review
- Neurosymbolic Reinforcement Learning and Planning: A Survey
- Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey
- LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification
- Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review
- Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
- Beyond Graph Neural Networks with Lifted Relational Neural Networks
- Faster-LTN: a neuro-symbolic, end-to-end object detection architecture
- Embedding and Extraction of Knowledge in Tree Ensemble Classifiers
- Building Human-like Communicative Intelligence: A Grounded Perspective
- A conditional, a fuzzy and a probabilistic interpretation of self-organising maps
- Natlog: a Lightweight Logic Programming Language with a Neuro-symbolic Touch
- Differentiable Inference of Temporal Logic Formulas
- Techniques for Symbol Grounding with SATNet
- Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art
- A Gaze into the Internal Logic of Graph Neural Networks, with Logic