Presentation Open Access

Learning from graphs: a spectral perspective

Defferrard, Michaël

The architecture of a neural network constrains the space of functions it can implement. Equivariance is one such constraint—enabling weight sharing and guaranteeing generalization. But symmetries alone might not be enough: for example, social networks, finite grids, and sampled spheres have few automorphisms. I will discuss how spectral graph theory yields vertex representations and a generalized convolution that shares weights beyond symmetries.

Files (2.7 MB)
Name Size
learning_from_graphs.pdf
md5:151dc77f72e1ea42ebf7624da6f7bc85
2.7 MB Download
108
91
views
downloads
All versions This version
Views 108108
Downloads 9191
Data volume 249.0 MB249.0 MB
Unique views 100100
Unique downloads 8484

Share

Cite as