5min chapter

Machine Learning Street Talk (MLST) cover image

#71 - ZAK JOST (Graph Neural Networks + Geometric DL) [UNPLUGGED]

Machine Learning Street Talk (MLST)

CHAPTER

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.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode