Network—feature dependencies using graph convolutional auto-encoders

Sébastien Lerique, Jacobo Levy-Abitbol, Márton Karsai & Éric Fleury

IXXI, École Normale Supérieure de Lyon

network—feature dependencies

Congruent

Incongruent

Socio-economic status

Language style

Topics

Network structure

25%

francophone

GMT/GMT+1

Sociolinguistics

GCN + Auto-encoders = 🎉💖🎉

node features

embedding

GCN

node features

adjacency matrix

Socio-economic status

Language style

Topics

Socio-economic status

Language style

Topics

Compressed & combined representation of nodes + network

Kipf & Welling (2016)

How is this useful

a.k.a., questions we can (will be able to) ask

how much can we compress network + features

(down to what dimension)

how well does feature set 1 + network structure predict feature set 2
(and how much does network structure help in predicting)

→ relative importance of network/feature in predicting links or clusters

Socioeconomic status

Language style

Speculation