Open buaawht opened 6 years ago
Hi, I think Node2vec is hard to deal with graph embedding in a dynamic Environment. Enhancement training is not precise if your graph structure apparently changed. I suggest that some graph deep learning method just like GCN you can try: training a stable neutral net and predicting new embedding vectors if the graph has changed.
hi, the graph is dynamic, so there are usually some new node added to the graph at any time. Is there some solution to the issue? I find word2vec can supply online trainhere, But how can i get the new sequences with the new nodes? Anyone who can help me?