Graph Neural Networks Workshop
|
The Third Seminar on Data Science and its ApplicationsFaculty of Mathematical Sciences, Ferdowsi University of MashhadGraph Theory and its Applications Lab
Wednesday, 2024/12/11 (21 Azar 1403), 14:00 - 16:00
In this workshop, we will only focus on the content of the second part of this page.
|
Graph Neural Networks Workshop
This workshop is designed to guide you through the fundamental concepts of graph neural networks (GNNs) and their applications. The workshop is divided into two main sections. In the first part, you’ll explore the principles of convolutional neural networks (CNNs) and how they can be applied to grid-structured data, such as images. This foundational knowledge will serve as a bridge to the exploration of graph neural networks in the second part of the workshop.
Part I: ANNs & CNNs in PyTorch
In this part of workshop, we’ll delve into the fascinating world of Neural Networks and Deep Learning with Python and Pytorch, where machines learn, adapt, and make decisions based on data. Topics that are covered are optmization, neural networks basics, perceptron model, mulit-layer perceptrons, convolutional neural networks, and some other related topics.
Part II: Graph Neural Networks in PyG
In the second part, you’ll learn how GNNs can be leveraged to solve a variety of tasks, including node classification, graph classification, and graph regression. You’ll have the opportunity to implement GNN models using the PyTorch Geometric library and apply them to real-world datasets, such as citation networks and molecular structures. Go to gta-lab.github.io/graph-neural-networks for more information.