Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective
Reviewed by Pithpith:AKTMNOZEopen to challenge →
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Semantic Channel Theory: Deductive Compression and Structural Fidelity for Multi-Agent Communication
Semantic channel theory achieves deductive compression where minimum block length under closure fidelity depends on the irredundant semantic core size rather than full knowledge-base size.
-
Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.
-
Persona-Trained Monte Carlo: Estimating Market-Outcome Distributions via Swarms of Persona-Conditioned Neural Policy Bots in a Limit Order Book
PTMC is a proposed Monte Carlo estimator that generates market-outcome distributions by simulating continuous double-auction interactions among persona-conditioned neural-policy bots whose heterogeneity is drawn from ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.