Joint graphfeature embeddings using GCAEs
Sébastien Lerique, Jacobo LevyAbitbol, Márton Karsai, Éric Fleury
IXXI, École Normale Supérieure de Lyon
Twitter users can...
... be tightly connected
... relate through similar interests
... write in similar styles
graph node2vec: \(d_n(u_i, u_j)\)
average user word2vec: \(d_w(u_i, u_j)\)
Questions

Create a taskindependent representation of network + features

What is the dependency between network structure and feature structure

Plot the cost of compressing network + features down to a given dimension \(n\)
network—feature dependencies
network—feature independence
Use deep learning to create embeddings
A framework
Graph convolutional neural networks + Autoencoders
How is this framework useful
Speculative questions we want to ask
Application and scaling
With great datasets come great computing headaches
Graphconvolutional neural networks
\(H^{(l+1)} = \sigma(H^{(l)}W^{(l)})\)
\(H^{(0)} = X\)
\(H^{(L)} = Z\)
\(H^{(l+1)} = \sigma(\color{DarkRed}{\tilde{D}^{\frac{1}{2}}\tilde{A}\tilde{D}^{\frac{1}{2}}}H^{(l)}W^{(l)})\)
\(H^{(0)} = X\)
\(H^{(L)} = Z\)
\(\color{DarkGreen}{\tilde{A} = A + I}\)
\(\color{DarkGreen}{\tilde{D}_{ii} = \sum_j \tilde{A}_{ij}}\)
Kipf & Welling (2016)
Neural networks
x
y
green
red
\(H^{(l+1)} = \sigma(H^{(l)}W^{(l)})\)
\(H^{(0)} = X\)
\(H^{(L)} = Z\)
Inspired by colah's blog
Semisupervised graphconvolution learning
Four wellmarked communities of size 10, small noise
More semisupervised GCN netflix
Overlapping communities of size 12, small noise
Two feature communities in a nearclique, small noise
Five wellmarked communities of size 20, moderate noise
(Variational) Autoencoders
From blog.keras.io
 Bottleneck compression → creates embeddings
 Flexible training objectives
 Free encoder/decoder architectures
high dimension
high dimension
low dimension
Example — autoencoding MNIST digits
MNIST Examples by Josef Steppan (CCBYSA 4.0)
60,000 training images
28x28 pixels
784 dims
784 dims
2D
From blog.keras.io
GCN + Variational autoencoders = 🎉💖🎉
node features
embedding
GCN
node features
adjacency matrix
Socioeconomic status
Language style
Topics
Socioeconomic status
Language style
Topics
Compressed & combined representation of nodes + network
Kipf & Welling (2016)
GCN+VAE learning
Five wellmarked communities of size 10, moderate label noise
Applications
a.k.a., questions we can (will be able to) ask
Explore the dependency between network structure and feature structure
Cost of compressing network + features down to a given dimension \(n\)
Taskindependent representation of network + features with uncertainty
Continuous change from feature communities to network communities
Speculation
Link prediction
Community detection
Graph reconstruction
Node classification
BlogCatalog compression cost
10,312 nodes
333,983 edges
39 groups
Full dataset
200 nodes
162 edges
36 groups
Toy model
Scaling GCN
node2vec, Grover & Leskovec (2016)
Walk on triangles
Walk outwards
Dataset  # nodes  # edges 

BlogCatalog  10K  333K 
Flickr  80K 
5.9M 
YouTube  1.1M  3M 
178K  44K 
✔
👷
👷
👷
Mutual mention network on 25% of the GMT+1/GMT+2 twittosphere in French
Minibatch sampling
node2vec, Grover & Leskovec (2016)
walk back \(\propto \frac{1}{p}\)
walk out \(\propto \frac{1}{q}\)
walk in triangle \(\propto 1\)
Walk on triangles — p=100, q=100
Walk out — p=1, q=.01
Thank you!
Sébastien Lerique, Jacobo LevyAbitbol, Márton Karsai, Éric Fleury
IXXI, École Normale Supérieure de Lyon
Joint graphfeature embeddings using GCAEs
By Sébastien Lerique