Add topic "Graph neural network" Accepted
Changes: 11

Add An Attempt at Demystifying Graph Deep Learning  Essays on Data Science
 Title

 Unchanged
 An Attempt at Demystifying Graph Deep Learning  Essays on Data Science
 Type

 Unchanged
 Article
 Created

 Unchanged
 20210719
 Description

 Unchanged
 There are a ton of great explainers of what graph neural networks are. However, I find that a lot of them go pretty deep into the math pretty quickly. Yet, we still are faced with that ageold problem: where are all the pics?? As such, just as I had attempted with Bayesian deep learning, I'd like to try to demystify graph deep learning as well, using every tool I have at my disposal to minimize the number of equations and maximize intuition using pictures. Here's my attempt, I hope you find it useful!
 Link

 Unchanged
 https://ericmjl.github.io/essaysondatascience/machinelearning/graphnets/
 Identifier

 Unchanged
 no value
Resource  v1  current (v1) 
Add Graph neural network
 Title

 Unchanged
 Graph neural network
 Description

 Unchanged
 A graph neural network (GNN) is a class of neural networks for processing data represented by graph data structures. They were popularized by their use in supervised learning on properties of various molecules. Since their inception, several variants of the simple message passing neural network (MPNN) framework have been proposed. These models optimize GNNs for use on larger graphs and apply them to domains such as social networks, citation networks, and online communities. It has been mathematically proven that GNNs are a weak form of the Weisfeiler–Lehman graph isomorphism test, so any GNN model is at least as powerful as this test. There is now growing interest in uniting GNNs with other socalled "geometric deep learning models" to better understand how and why these models work.
 Link

 Unchanged
 https://en.wikipedia.org/?curid=68162942
Topic  v1  current (v1) 
Add Graph neural network treated in An Attempt at Demystifying Graph Deep Learning  Essays on Data Science
 Current
 treated in
Topic to resource relation  v1 
Add Deep learning prerequisite for An Attempt at Demystifying Graph Deep Learning  Essays on Data Science
 Current
 prerequisite for
Topic to resource relation  v1 
Add Graph convolutional networks (GCN) is Graph neural network
 Current
 is
Topic to topic relation  v1 
Add Deep learning parent of Graph neural network
 Current
 parent of
Topic to topic relation  v1 
Delete Graph convolutional networks (GCN) (detached) PyTorch geometric
 Current
 (detached)
 At edit time
 uses
Topic to topic relation  v2 
Add PyTorch geometric uses Graph neural network
 Current
 uses
Topic to topic relation  v1 
Delete Deep learning (detached) Graph convolutional networks (GCN)
 Current
 (detached)
 At edit time
 parent of
Topic to topic relation  v2 
Delete Graph convolutional networks (GCN) (detached) Spektral
 Current
 (detached)
 At edit time
 uses
Topic to topic relation  v2 
Add Spektral uses Graph neural network
 Current
 uses
Topic to topic relation  v1