Sparse Graph Neural Networks with Scikit-network

Thomas Bonald (1, 2) , Simon Delarue (1, 2, 3, 4)

1 DIG - Data, Intelligence and Graphs
2 INFRES - Département Informatique et Réseaux
3 NOS - Numérique, Organisation et Société
4 SES - Département Sciences Economiques et Sociales

In recent years, Graph Neural Networks (GNNs) have undergone rapid development and have become an essential tool for building representations of complex relational data. Large real-world graphs, characterised by sparsity in relations and features, necessitate dedicated tools that existing dense tensor-centred approaches cannot easily provide. To address this need, we introduce a GNNs module in Scikit-network, a Python package for graph analysis, leveraging sparse matrices for both graph structures and features. Our contribution enhances GNNs efficiency without requiring access to significant computational resources, unifies graph analysis algorithms and GNNs in the same framework, and prioritises user-friendliness.

Keywords: Graph Neural Networks; Sparse Matrices; Python

Domains: Artificial Intelligence [cs.AI]

Thomas Bonald, Simon Delarue. Sparse Graph Neural Networks with Scikit-network. Complex Networks, 2023, Menton, France. ⟨hal-04277248⟩