Question about mini-batches training for hypergraph neural network

Questions
#1

Is it possible to realize mini-batch training in hypergraph neural network by using some graph sampler (like GraphSAINT or GraphSAGE)?

I guess it is possible to achieve it by these built graph samplers like dgl.sampling based on the example here? I am very interested in this and wondering if you can give me some insights. Any suggestions would be helpful!

#2

In general, we can always build a bipartite graph that corresponds to a hypergraph. There will be two types of nodes in the bipartite graph that correspond to the raw nodes and hyperedges. You can then use a built-in DGL sampler.

1 Like
#3

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.