Graph Neural Networks

These networks learn from data shaped as nodes and edges, such as molecules, social networks and financial transaction networks. Their shared idea is message passing: each node gathers information from its neighbours and then updates its representation, so the influence of distant nodes arrives after several layers. The variants differ in how they aggregate: a degree-weighted average in GCN, learned attention weights in GAT, a sample of neighbours in GraphSAGE, and a sum that preserves discriminative power in GIN.

Basic2009

Graph Neural Network

Graph Neural Network (GNN)

A family of models that learn a representation for each node by exchanging messages with its neighbours along the edges, combining node features with graph structure.

Graph Neural Networks

Basic2017

Graph Convolutional Network

Graph Convolutional Network (GCN)

A simple graph layer that takes a normalised average of the representations of a node and its neighbours and then applies a shared linear transformation; it is a first-o…

Graph Neural Networks

Intermediate2018

Graph Attention Network

Graph Attention Network (GAT)

It replaces GCN's fixed weights with learned attention coefficients for each edge, so each node decides how important each neighbour is, with multiple attention heads.

Graph Neural Networks

Basic2017

GraphSAGE

GraphSAGE

An inductive framework that learns aggregation functions over a sampled neighbourhood, so it can compute representations for new nodes the network did not see during tra…

Graph Neural Networks

Intermediate2019

Graph Isomorphism Network

Graph Isomorphism Network (GIN)

A GNN designed to reach the discriminative power of the Weisfeiler–Lehman test (1-WL), using sum aggregation and an MLP in the update.

Graph Neural Networks

Intermediate2018

Relational Graph Convolutional Network

Relational Graph Convolutional Network (R-GCN)

An extension of GCN for multi-relational graphs (such as knowledge graphs) that uses a different weight for each relation type, with a weight decomposition to reduce par…

Graph Neural Networks

Advanced2020

Graph Transformer

Graph Transformer (GT)

Applying self-attention to the nodes of a graph with positional or structural encodings (such as Laplacian eigenvectors) so the model knows the graph's structure, going…

Graph Neural NetworksSpecialized ArchitecturesTransformer Architectures

Advanced2020

Temporal Graph Networks

Temporal Graph Networks (TGN)

A framework for learning representations on dynamic graphs represented as a stream of timed events, using a memory for each node that is updated by events and an embeddi…

Temporal and Sequential NetworksGraph Neural Networks