AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
#71 - ZAK JOST (Graph Neural Networks + Geometric DL) [UNPLUGGED]
Machine Learning Street Talk (MLST)
The Over Smoothing Problem
The over smoothing problem is that, even if you don't over smooth, you're gathering a lot of information. And then eventually they're pulling in things from far away, and you're just making this big homogeneous blob. The number of possible configurations explodes if your receptive field is increasing expedentially. There's lots of different approaches out there, but ou're exactly right. It's not trivial to just make g and ends deeper because of this expeditual increase in the receptive field.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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