search

snap-stanford / neural-subgraph-learning-GNN

340 stars 64 forks source link

Query graph geolocalization on target graph and usage of graph attributes #31

Open JianliWei1995 opened 1 year ago

JianliWei1995 commented 1 year ago

Congratutations on your great work on graph matching. Here I have two concerns hoping to get your reply.

  1. On another issue you replied 'To identify where the query graph appears within the target graph, one can make use of the outputted alignment matrices -- subgraph_matching/alignment.py outputs such a matrix'. So far do you have any updates on this problem that could accurately achieve localization?
  2. You also replied that you have a new version using graph node labels? Can you please send me (wei.909@osu.edu) a copy of code doing that ? Have you ever tried use more graph attributes such as node feature, edge label or edge feature to improve your graph matching performance?

Thanks,