Machine Learning Street Talk (MLST) cover image

#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]

Machine Learning Street Talk (MLST)

CHAPTER

Exploring Graph Curvature and Bottlenecks in Message Passing

This chapter examines the impact of graph curvature, particularly negative curvature, on the occurrence of bottlenecks within graph structures. It highlights the tension between sparsity, low bottlenecks, and positive curvature while proposing future research into the effects of mildly negative curvature on optimal message propagation.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner