Understanding Graph Convolutional Networks

Description
Speaker
We often encounter interconnected data in our work—from molecular structure, to gene and protein interactions to addresses and streets on a map, to connections in a social network–so much of the world is better understood when we address its connections.

Since the so-called “deep learning revolution”, remarkable improvements have been made by RNNs, CNNs, GANs, and more – driving fields such as computer vision and natural language processing forward by leaps and bounds. We often encounter instances, though, where it’s the relationships between our data as well as the data itself that we need to consider fully, and sometimes Euclidean representations fall short.

Graph Neural Networks have become a hotter and hotter topic in recent years. Since 2014, approaching deep learning with graph-structured data has become less and less niche, and many improvements have been made in algorithms that make predicting on graph-structured data possible. However, even within the term “Graph Neural Networks”, there are a variety of vastly different approaches, and lots of hype. So, what can GNNs do for you?

In this discussion, we’ll focus on:
• Breaking down the terminology – what are Graph Neural Networks versus Graph
Convolutional Networks, and what are some other kinds of GNNs?
• Dissecting the intuition behind Graph Convolutional Networks – what makes them work?
• How to get started embedding and predicting on benchmark biological datasets with an implementation of a Graph Convolutional Network.

Sidney Arcidiacono

Data Science Intern at GreenLight Biosciences.
  • Date: Sep 07, 10:00 (US Pacific Time)
  • Fee: Free
  • Available Seats: 238 (max 500)
  • Help? Send Question
Watch Recording