Graph Neural Network

Intermediate

Neural networks that operate on graph-structured data by propagating information along edges.

Full Definition

Neural networks that operate on graph-structured data by propagating information along edges.

Keywords

nodes edges

Domains

Model Architectures

Related Terms

Neural Network narrower than

A parameterized function composed of interconnected units organized in layers with nonlinear activations.

 Message Passing Neural Network related to

GNN framework where nodes iteratively exchange and aggregate messages from neighbors.

 Graph Convolution related to

Extension of convolution to graph domains using adjacency structure.

 Graph Attention Network related to

GNN using attention to weight neighbor contributions dynamically.

 Heterogeneous Graph related to

Graphs containing multiple node or edge types with different semantics.

Concept Map

See how Graph Neural Network connects to other concepts.

Open Knowledge Graph