Unveiling the Power of Graphs: Node and Edge Classification w/ GraphSAGE | GraphML

Full code example of Node and Edge classification with GraphSAGE for GraphML. DGL on PyTorch backbone. Graph Neural Networks explained.

One of the most popular and widely adopted tasks for graph neural networks is node classification, where each node in the training/validation/test set is assigned a ground truth category from a set of predefined categories.

To classify nodes, graph neural network performs message passing to utilize the node’s own features, but also its neighboring node and edge features.

All credits to

00:00 Intro
02:10 Code DGL
02:50 Code Node Classification
13:27 Heterogeneous Graph Node Classification
15:00 Code EDGE Classification
26:33 Heterogeneous Graph Edge Classification

#graphs
#machinelearning
#datascience

[KolliMadhukar]

Can you share the link to the collab notebook

[_________]

Not sure if it’s because of a poor connection but from timestamp 6:24, the video quality gets really bad.

[ShahryarSalmani]

Thank you for your series of tutorials, PLEASE name your playlist more clear. For example this playlist could be Graph Neural Networks From Scratch.

[InfoDailyDose]

Every thing in the video was beautiful (Y)

[lubnashaikh]

Can you please drop this code. I need it for reference.