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

Описание: PyData Cyprus Meetup - May 2021


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.





www.pydata.org

PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.

PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.

Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVi...