Tuple Packing: Efficient Batching of Small Graphs in Graph Neural Networks. (arXiv:2209.06354v1 [cs.LG])

When processing a batch of graphs in machine learning models such as Graph
Neural Networks (GNN), it is common to combine several small graphs into one
overall graph to accelerate processing and reduce the overhead of padding. This
is for example supported in the PyG library. However, the sizes of small graphs
can vary substantially with respect to the number of nodes and edges, and hence
the size of the combined graph can still vary considerably, especially for
small batch …

arxiv batching graph graph neural networks graphs networks neural networks small