But I think you can do more experiment about the node classification. Since I think the fixed split on nodes is not enough. Maybe the random split on nodes can give more convincing results.
Hi, thank for your advice. That is true. But to make it easier for preparation, we use the same splits as previous node classification methods. We may add more experiments in the future. Thank you.
But I think you can do more experiment about the node classification. Since I think the fixed split on nodes is not enough. Maybe the random split on nodes can give more convincing results.