Advanced Graph Neural Networks

سرفصل های دوره

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.

01 - Introduction

01 - Overview of graph neural networks

02 - Prerequisites

02 - 1. Overview of Graph Neural Networks

01 - Message passing in GNNs

02 - Aggregation and transformation math

03 - Aggregation and transformation math in matrix form

03 - 2. Node Classification with Graph Attention Networks

01 - Introducing graph attention

02 - Computing the attention coefficient

03 - Including attention in GNN layers

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

05 - Exploring the Cora dataset

06 - Setting up the graph convolutional network

07 - Training a graph convolutional network

08 - Node classification using a graph attention network

09 - Using the GATv2Conv layer for attention

04 - 3. Graph Classification Using Graph Convolution

01 - Understanding graph classification

02 - Exploring the PROTEINS Dataset for graph classification

03 - Minibatching graph data

04 - Setting up a graph classification model

05 - Training a GNN for graph classification

06 - Eliminating neighborhood normalization and skip connections

05 - 4. Link Prediction Using Graph Autoencoders

01 - A quick overview of autoencoders

02 - Introducing graph autoencoders

03 - Splitting link prediction data

04 - Understanding link splits

05 - Designing an autoencoder for link prediction

06 - Training the autoencoder

06 - Conclusion

01 - Summary and next steps

439,000 تومان

افزودن به سبد خرید

خرید دانلودی فوری

در این روش نیاز به افزودن محصول به سبد خرید و تکمیل اطلاعات نیست و شما پس از وارد کردن ایمیل خود و طی کردن مراحل پرداخت لینک های دریافت محصولات را در ایمیل خود دریافت خواهید کرد.

تولید کننده: LinkedIn Learning (Lynda)