How powerful are Graph Convolutions? (review of Kipf & Welling, 2016)

Resource | v1 | created by janarez |
Type Blog post
Created 2016-09-13
Identifier unavailable


This post is about a paper that has just come out recently on practical generalizations of convolutional layers to graphs: Thomas N. Kipf and Max Welling (2016) Semi-Supervised Classification with Graph Convolutional Networks Along the way I found this earlier, related paper: Defferrard, Bresson and Vandergheynst (NIPS 2016) Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering This post is mainly a review of (Kipf and Welling, 2016). The paper is nice to read, and while I like the general idea, I feel like the approximations made in the paper are too limiting and severely hurt the generality of the models we can build. This post explains why.


gives pros/cons of Graph convolutional networks (GCN)

Generalization of neural networks to arbitrary graphs.

Currently, no authors are attached.

reviews Graph convolutional networks

Many important real-world datasets come in the form of graphs or networks: social networks, knowledge...

Edit resource New resource

8.0 /10
useless alright awesome
from 1 review
Write comment Rate resource Tip: Rating is anonymous unless you also write a comment.
Resource level 4.0 /10
beginner intermediate advanced
Resource clarity 9.0 /10
hardly clear sometimes unclear perfectly clear
Reviewer's background 3.0 /10
none basics intermediate advanced expert
Comments 0
Currently, there aren't any comments.