Graph Neural Networks
Petar delves into using category theory to enhance graph neural networks, simulating classical computer science algorithms. By leveraging commutative diagrams, they align GNNs with target algorithms, offering a functional programming-like type checker for representations.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#85 Dr. Petar Veličković (Deepmind) - Categories, Graphs, Reasoning [NEURIPS22 UNPLUGGED]
Related Questions