Graph neural network: Difference between revisions

Revision as of 20:51, 28 June 2021

Revision as of 20:53, 28 June 2021

Line 5:

== Pipeline of GNN model ==

The design pipeline for a GNN model can be generally derived as four steps: find graph structure, specify graph, build model, and design loss functions.

[[File:Pipe-line of GNN.png|thumb|558x558px|The general design pipeline for a GNN model.<ref>{{Cite journal|date=2020-01-01|title=Graph neural networks: A review of methods and applications|url=https://www.sciencedirect.com/science/article/pii/S2666651021000012|journal=AI Open|language=en|volume=1|pages=57–81|doi=10.1016/j.aiopen.2021.01.001|issn=2666-6510}}</ref>]]

=== Find graph structure ===

Line 16:

=== Specify graph ===

[[File:Scene graph example.png|thumb|529x529px|An example of scene graph.]]

[[File:Scene graph example.png|thumb|529x529px|An example of scene graph.<ref>{{Cite journal|last=Johnson|first=Justin|last2=Krishna|first2=Ranjay|last3=Stark|first3=Michael|last4=Li|first4=Li-Jia|last5=Shamma|first5=David A.|last6=Bernstein|first6=Michael S.|last7=Fei-Fei|first7=Li|date=2015-06|title=Image retrieval using scene graphs|url=https://ieeexplore.ieee.org/document/7298990|journal=2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)|pages=3668–3678|doi=10.1109/CVPR.2015.7298990}}</ref>]]

After a graph structure is found in the given data, the type of this graph should also be specified. A graph can be simply categorize as [[Directed graph|directed]]/[[Undirected graph|undirected]] or [[Homogeneous graph|homogeneous]]/[[Heterogeneous graph|heterogeneous]]. Note that for heterogeneous graphs, each edge may differ to the others by its property. For example, each edge in a [[scene graph]]<ref>{{Cite journal|last=Johnson|first=Justin|last2=Krishna|first2=Ranjay|last3=Stark|first3=Michael|last4=Li|first4=Li-Jia|last5=Shamma|first5=David A.|last6=Bernstein|first6=Michael S.|last7=Fei-Fei|first7=Li|date=2015-06|title=Image retrieval using scene graphs|url=https://ieeexplore.ieee.org/document/7298990|journal=2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)|pages=3668–3678|doi=10.1109/CVPR.2015.7298990}}</ref> has different meaning to represent the relation between nodes.

=== Design loss function ===