Thanks for the proposal! We are very interested in improving search algorithms and cost model. I was very excited to read about FamilySeer a week ago.
In terms of the subgraph similarity, AFAIK @comaniac and @zxybazh have been working independently on this topic to improve overall search time; On cost model, @merrymercy and I have been working on a project called TenSet to train a more effective cost model, where we do have task embeddings etc 
Looking forward to close collaboration on your PRs