Open jexterliangsufe opened 1 year ago
My graph: tens of millions edges and 70000 nodes My model is something like GCNConv+GRU(GRU's reset, update and the other part is GCNConv)
Problem: cuda memory usage becomes bigger and bigger as time steps add.
How can I revise GNN part or RNNs part to solve this?
My graph: tens of millions edges and 70000 nodes My model is something like GCNConv+GRU(GRU's reset, update and the other part is GCNConv)
Problem: cuda memory usage becomes bigger and bigger as time steps add.
How can I revise GNN part or RNNs part to solve this?