Applying ML on graph-structured data - an introduction to Graph Neural Networks

PyData Cyprus welcomes you to our 4th meetup of 2021!

The event will be online on Zoom and the link will be visible if you RSVP.

Kefei, from nate, will give an intro to the theory of Graph Neural Networks and a small demo for entity classification using Pytorch Geometric.

= Abstract =

A graph is a data structure consisting of two components, nodes and edges. It is useful for modelling relationships and interactions between interconnected entities.

Many types of data can naturally be represented this way, such as social networks, molecule interactions or even websites. Leveraging the relational structure gives us the potential to build more accurate models for classification, prediction and clustering.

This talk introduces Graph Neural Networks (GNNs), a class of models designed to perform inference on such interconnected data. They are well suited for a wide range of applications from drug discovery to recommender systems and traffic prediction.

We will cover the theory of GNNs, specifically how they work and scale to large graphs, as well as a small demo of a GNN for entity classification using Stellar Graph.

= About the speaker =

Kefei Hu is a Research Scientist at nate (www.nate.tech), a New York based e-commerce startup that leverages ML to automate online purchases for customers. She graduated with MSc in Data Science & Machine Learning from UCL in 2019, with an area of interests in Natural Language Processing, Representation Learning & everything to do with graphs.