Advanced Graph Neural Networks

Focused View

Janani Ravi

2:04:23

0 View

01 - Introduction

01 - Overview of graph neural networks.mp4

06:45

02 - Prerequisites.mp4

01:00

02 - 1. Overview of Graph Neural Networks

01 - Message passing in GNNs.mp4

04:10

02 - Aggregation and transformation math.mp4

04:54

03 - Aggregation and transformation math in matrix form.mp4

04:11

03 - 2. Node Classification with Graph Attention Networks

01 - Introducing graph attention.mp4

04:07

02 - Computing the attention coefficient.mp4

04:14

03 - Including attention in GNN layers.mp4

03:10

04 - Getting set up with Colab and the PyTorch Geometric library.mp4

03:01

05 - Exploring the Cora dataset.mp4

06:31

06 - Setting up the graph convolutional network.mp4

04:51

07 - Training a graph convolutional network.mp4

06:25

08 - Node classification using a graph attention network.mp4

05:52

09 - Using the GATv2Conv layer for attention.mp4

03:23

04 - 3. Graph Classification Using Graph Convolution

01 - Understanding graph classification.mp4

06:32

02 - Exploring the PROTEINS Dataset for graph classification.mp4

05:19

03 - Minibatching graph data.mp4

02:47

04 - Setting up a graph classification model.mp4

04:49

05 - Training a GNN for graph classification.mp4

04:39

06 - Eliminating neighborhood normalization and skip connections.mp4

03:39

05 - 4. Link Prediction Using Graph Autoencoders

01 - A quick overview of autoencoders.mp4

03:15

02 - Introducing graph autoencoders.mp4

03:19

03 - Splitting link prediction data.mp4

05:46

04 - Understanding link splits.mp4

06:02

05 - Designing an autoencoder for link prediction.mp4

06:03

06 - Training the autoencoder.mp4

07:46

06 - Conclusion

01 - Summary and next steps.mp4

01:53

Description

Explore graph neural networks (GNNs) in depth. Instructor Janani Ravi begins by delving into the workings of GNNs, covering message passing, aggregation, transformation, transformation math, and attention mechanisms like GATv2Conv. Janani explores practical applications such as node classification, graph classification, and link prediction using datasets like Cora and PROTEINS. Hands-on exercises on Colab with PyTorch Geometric provide experience in setting up and training GNN models. Learn about mini-batching and neighborhood normalization to tackle graph data challenges. This course is ideal for researchers, data scientists, and anyone interested in deep learning or graph theory. Tune in to unlock new potentials in data analysis and modeling with GNNs.

More details

User Reviews

Rating

average 0

Total votes0

Focused display

Neural Networks

Janani Ravi

Instructor's Courses

Linkedin Learning

View courses Linkedin Learning

LinkedIn Learning is an American online learning provider. It provides video courses taught by industry experts in software, creative, and business skills. It is a subsidiary of LinkedIn. All the courses on LinkedIn fall into four categories: Business, Creative, Technology and Certifications. It was founded in 1995 by Lynda Weinman as Lynda.com before being acquired by LinkedIn in 2015. Microsoft acquired LinkedIn in December 2016.