Graph Neural Networks - From Theory to Practice

This talk was led by our very own Satwant Singh! Satwant is a final year Applied Data Science student who has extensive research and industry experience in machine learning.

Graph neural networks are a type of deep learning algorithm that are designed to work with graph-structured data.

During the talk, Satwant provided an overview of what Graph Neural Networks are, how they work, and their applications in various fields, such as social network analysis, recommender systems, and drug discovery. He also discussed the challenges of working with graph-structured data and how graph neural networks can help overcome some of these challenges.

He also presented examples of how Graph Neural Networks have been used in real-world applications and provide insights into the advantages and limitations of these models. He also demonstrated how to build and train a graph neural network using pytorch and even had a brief session group session on a google collab notebook!

Overall, this talk on Graph Neural Networks was an opportunity for students and other interested individuals to learn about this exciting area of machine learning and to gain insights into how it can be applied to solve complex problems in various fields.