Do you want to know Graph Neural Networks (GNN) implementation in Python?
Prodramp
[Graph Neural Networks Part 2/2]: This tutorial is part 2 of a two parts GNN series.
You will learn GNN technical details along with hands on exercise using Python programming along with NetworkX, PyG (pytorch_geometric) , matplotlib libraries. The tutorial covers following topics in 4 Jupyter notebooks and a pdf presentation:
- Graph representations -- Adjacency Matrix -- Feature Matrix -- Incidence Matrix -- Degree Matrix -- Laplacian Matrix
- Bag of Nodes
- Node Embedding and Node Embedding Space
- Applying Convolution to Graph similar to Image
- Message Passing
- Understanding Graph Datasets available in PyG
- Node Classification using MLP & GNN
- NetworkX and tSNE visualization of Graphs
- GNN Explainer
Part 1 (https://youtu.be/YdGN-J322y4):
- Fundamentals of Graph
- Mathematics of Graph
- Introduction to NetworkX Python Package
- Graph Programming with NetworkX
- Introduction to GNN
- Relationship between GNN and CNN
- Introduction to PyG (pytorch_geometric)
- Graph Visualization Tools - yEd
- Various Graph Data Manipulation
ā¬ā¬ā¬ā¬ā¬ā¬ ā° TUTORIAL TIME STAMPS ā° ā¬ā¬ā¬ā¬ā¬ā¬
- (00:00) Video Starts
- (00:08) Video Introduction
- (00:50) Tutorial Content in Part2
- (05:54) Graph Representations Techniques
- (06:20) Adjacency Matrix
- (09:12) Incidence Matrix
- (11:44) Degree Matrix
- (12:10) Laplacian Matrix
- (14:46) Creating Graph with NetworkX (Jupyter notebook)
- (22:25) Graph Visualization with Node classes (Jupyter notebook)
- (25:10) Graph Visualization with Node and Edge Labels (Jupyter notebook)
- (32:30) Nodes Adjacency List (Jupyter notebook)
- (35:50) Bag of Nodes
- (36:45) Graph Walking (Jupyter notebook)
- (42:59) GNN Concepts
- (44:01) Role of Laplacian Matrix
- (45:52) Convolution in Images
- (49:23) Graph vs 2D fixed data types i.e. images, text
- (51:39) Convolution on Graphs, how?
- (52:25) Graph Feature Matrix
- (53:11) Applying Convolution in Graphs
- (54:49) Node Embeddings
- (01:01:37) Message Passing in GNN
- (01:05:15) Advantages of Node Embeddings
- (01:06:12) GNN Use Cases
- (01:07:36) Handling data in PyG (Jupyter notebook)
- (01:27:40) GNN Experiment for Node grouping (Jupyter notebook)
- (01:31:53) Node assignment to proper class ((Jupyter notebook)
- (01:41:47) GNN Model visualization with Netron
- (01:42:57) Node classification using GNN in PyG
- (01:51:22) Graph tSNE Visualization
- (01:51:44) GNN Explainer
- (01:55:45) Recap
Google colab notebooks used in this tutorial: -https://github.com/prodramp/DeepWorks/tree/main/GraphNeuralNetworks
Part 2 PDF document: https://github.com/prodramp/DeepWorks/blob/main/GraphNeuralNetworks/Graph%20Neural%20Networks%20-%20Part2.pdf
Please visit:
- Prodramp LLC | https://prodramp.com | @prodramp
- https://www.linkedin.com/company/prodramp
Content Creator: Avkash Chauhan (@avkashchauhan)
Tags: #ai #ml #gnn #mlops #aicloud #h2oai #driverlessai #machinelearning #cloud #mlops #model #collaboration #deeplearning #modelserving #modeldeployment #keras #tensorflow #pytorch #datarobot #datahub #aiplatform #aicloud #modelperformance #modelfit #modeleffect #modelimpact #modelbias #modeldeployment #modelregistery #modelpipeline #neptuneai #streamlit #pythonapps #deepchecks #modeltesting #codeartifact #dataartifact #modelartifact #onnx #aws #supervisor #supervisord #kaggle #keplergl #mapbox #lightgbm #xgboost #classification #regression #dataengineering #pandas #keras #tensorflow #tensorboard #mnist #cnn #convnet #alexnet #prodramp #avkashchauhan #cnnexplainer #gnn #graph #graphneuralnetwork #pyg #networkx #yed #gephi ... https://www.youtube.com/watch?v=VDzrvhgyxsU
384212741 Bytes