Graph Neural Networks
Petar discusses how altering the connectivity in graph neural networks can improve performance without increasing parameters. He also explores the implications of negatively curved graphs on bottleneck formation and scalability, challenging existing theories in the field.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]
Related Questions