Sparse Graph Neural Networks with Scikit-network
Abstract
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.
Domains
Artificial Intelligence [cs.AI]
Fichier principal
Sparse_Graph_Neural_Networks_with_Scikit_network.pdf (325.94 Ko)
Télécharger le fichier
Origin | Files produced by the author(s) |
---|