2

While there has been a lot of talk about defining the similarity between nodes in the embedding space, I don't seem to come across any talking about defining the similarity between nodes in the original, non-embedded graph. Any suggestions as to how to explain such?

Pustam Raut
  • 107
  • 1
  • 1
  • 3
Student
  • 421
  • 2
  • 10

1 Answers1

0

If the nodes you mention have inherent features, you could encode the features in a way that is similar. For example, nodes involving user data could have features like location, gender, etc.

And if you mean similarity in terms of connected/neighboring edges, you could probably define your own node feature vector such as one-hot encoding to the nodes it is connected to ( like an adjacency matrix).

Amirtha Varshini A S
  • 11
  • 2