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

Resource history | v1 (current) | created by janarez on Apr 1, 2021

Details

Title: How powerful are Graph Convolutions? (review of Kipf & Welling, 2016)
Type: BlogPost
Created: 2016-09-13
Description: 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.
Link: https://www.inference.vc/how-powerful-are-graph-convolutions-review-of-kipf-welling-2016-2/
Identifier: no value

This resource has no history of related authors.