liveBook · Manning

Graph attention network

As explained in Build AI Drug Discovery Pipelines

A graph attention network is a graph neural network architecture that uses attention weights to aggregate information from neighboring nodes.

A graph attention network (GAT) is a graph neural network that learns how strongly each neighboring node should influence a node’s representation. In molecular graphs, this can emphasize neighbors belonging to important functional groups. section 11.5.4

Compared with graph convolutional aggregation, GAT provides:

  • Learned edge weights based on node features rather than fixed degree normalization. section 11.5.4
  • Multi-head attention, which learns multiple neighborhood patterns and concatenates or averages their outputs. section 11.5.4
  • More interpretable attention weights, with intermediate expressiveness between GCN and GIN. section 11.5.4

Molecular graph layer

A two-head GAT layer can replace a graph convolution layer while averaging the two attention outputs: self.mol_conv1 = GATConv(num_features_mol, num_features_mol, heads=2, concat=False). section 11.5.4

For drug-target affinity prediction, GAT is evaluated alongside GCN and GIN on DAVIS and KIBA subsets; full dual-graph training can require several hours on a modern GPU. section 11.6

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains learned weights and multi-head aggregation, then stops short of detailed attention equations or optimization.
Examples
Uses functional-group neighbors, a two-head GATConv layer, and DAVIS and KIBA evaluation subsets.
What it assumes
Assumes familiarity with graph neural networks, node features, neighborhood aggregation, and graph convolutional layers.
What you can do after
Apply it by replacing graph convolution layers with multi-head attention layers in a molecular graph model.
How it connects
Connects graph attention networks with graph convolutional networks, graph isomorphism networks, molecular graphs, and drug-target affinity prediction.

Also explained in

Compare how 4 books explain graph attention network →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.