Spektral
  • Home

Tutorials

  • Getting started
  • Data modes
  • Creating a dataset
  • Creating a layer
  • Examples
    • Node-level prediction
    • Graph-level prediction
    • Other applications

Layers

  • Convolutional layers
  • Pooling layers
  • Base layers
  • Models

Data

  • Containers
  • Datasets
  • Loaders
  • Transforms

Utils

  • Convolution
  • Sparse
  • Miscellaneous

Other

  • External resources
  • About
Spektral
  • Docs »
  • Tutorials »
  • Examples

Examples

This is a collection of examples that you can use as template for your projects.

Node-level prediction

  • Citation networks with GCN
  • Citation networks with GCN (custom training loop)
  • Citation networks with ChebConv
  • Citation networks with GAT
  • Citation networks with GAT (custom training loop)
  • Citation networks with ARMA
  • Citation networks with SimpleGCN (custom transform)
  • Open Graph Benchmark dataset

Graph-level prediction

  • General GNN
  • Custom dataset
  • OGB mol-hiv classification (edge attributes)
  • QM9 regression with ECC (custom training loop)
  • QM9 regression with ECC (batch mode)
  • TUDataset classification with GIN
  • TUDataset classification with MinCut pooling

Other applications

  • Graph signal classification on MNIST (mixed mode)
  • Node clustering on citation networks with MinCut pooling (unsupervised)
  • Link prediction with Variational Graph Autoencoders (by Filippo Bianchi)
Next Previous

Built with MkDocs using a theme provided by Read the Docs.
GitHub « Previous Next »