AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Message Passing - The Four Hundredth Transform
The way they basically did this was they defined the forty e transform, and then they approximated it as a polynomial in the adjacent matrix. So why would you do that? Well, if you take a a set of features for your notes and you multiply it by the adjacency matrix, that does message passing. And what that does is that localizes the information to be in a one hop neighborhood.