This talk will provide an introduction to Graph Neural Networks and motivate their usage. We will go through a brief overview of the various classes of networks i.e. message passing networks, graph convolutional networks, and graph attention networks, and talk about each of them in detail. We will discuss the strengths and weaknesses of each type of networks and how they can be used for different tasks.
What format do you have in mind for your talk?
Talk
Table of contents
Basic Introduction to Graphs and key terms related to them
Motivation behind Graph Neural Networks
Brief Overview of the various classes of networks
Overview of Message Passing Graph Neural Networks
Overview of Graph Convolutional Networks
Overview of Graph Attention Networks
Recommended Reading and Next Steps
What domain would you say your talk falls under?
Data Science & Machine Learning
Duration in minutes (including Q&A)
40-60
Prerequisites
Basic background knowledge about Machine Learning, no advanced knowledge about maths or deep learning is required.
Speaker bio
Saurav Maheshkar is a Research Machine Learning Engineer at Re:courseAI, where he works on Geometric Deep Learning. He studies Computer Science at the University of Manchester with a passion for geometric learning and self-supervised learning. He is currently working on developing self-supervised learning methods for graphs, and is also interested in benchmarking self-supervised learning methods and knowledge distillation methods.
Title of the talk
Introduction to Graph Neural Networks
Description
This talk will provide an introduction to Graph Neural Networks and motivate their usage. We will go through a brief overview of the various classes of networks i.e. message passing networks, graph convolutional networks, and graph attention networks, and talk about each of them in detail. We will discuss the strengths and weaknesses of each type of networks and how they can be used for different tasks.
What format do you have in mind for your talk?
Talk
Table of contents
What domain would you say your talk falls under?
Data Science & Machine Learning
Duration in minutes (including Q&A)
40-60
Prerequisites
Basic background knowledge about Machine Learning, no advanced knowledge about maths or deep learning is required.
Speaker bio
Saurav Maheshkar is a Research Machine Learning Engineer at Re:courseAI, where he works on Geometric Deep Learning. He studies Computer Science at the University of Manchester with a passion for geometric learning and self-supervised learning. He is currently working on developing self-supervised learning methods for graphs, and is also interested in benchmarking self-supervised learning methods and knowledge distillation methods.
Twitter/X: @MaheshkarSaurav LinkedIn: Saurav Maheshkar
The talk/workshop speaker agrees to
[X] Share the slides, code snippets and other material used during the talk
[X] If the talk is recorded, you grant the permission to release the video on BangPyper's YouTube channel under CC-BY-4.0 license
[X] Not do any hiring pitches during the talk and follow the Code of Conduct