How to batch sequential graphs?


For a batch, I am taking a sliding window of all articles mentioned within specific time intervals with significant overlap. For example, one graph/label pair is made out of [0,5], the next out of [1,6], and [2,7], and so on.

I think it’s wasteful to generate a ton of duplicate nodes, but also the logic for reusing the nodes seems complex. What’s the best way to train over batches of graphs that have very similar structures?


You can build it into a big graph. And using send_and_recv function to select a subgraph to do message passing each time. Hope this could help!