A comprehensive survey on graph neural networks
A comprehensive survey on graph neural networks Wu et al., arXiv’19
Last year we looked at ‘Relational inductive biases, deep learning, and graph networks,’ where the authors made the case for deep learning with structured representations, which are naturally represented as graphs. Today’s paper choice provides us with a broad sweep of the graph neural network landscape. It’s a survey paper, so you’ll find details on the key approaches and representative papers, as well as information on commonly used datasets and benchmark performance on them.
We’ll be talking about graphs as defined by a tuple where
is the set of nodes (vertices),
is the set of edges, and A is the adjacency matrix. An edge is a pair
, and the adjacency matrix is an
(for N nodes) matrix where
if nodes
and
are not directly connected by a edge, and some weight value > 0 if they are.
In an attributed graph we also have a set of attributes for each node. For node attributes with D dimensions we have a node feature matrix .
A spatial-temporal graph is one where the feature matrix evolves over time. It is defined as
with
for
time Continue reading