Some application advisory

Thank you very much for your work.
I read the two examples test_graph and boolean_logic. And now my question is if I hope your project can be used for deep learning graph optimization. For example, graph merging, graph replacement. What changes do you think I should make to e node and e class?
Or which part of the code do you think I should focus on learning so that I can fully understand the implementation of egraph?

Thank you very much, looking forward to your reply.