Sep 23–26, 2019

An introduction to machine learning on graphs

David Mack (Octavian)
3:45pm4:25pm Thursday, September 26, 2019
Location: 1A 12
Secondary topics:  Financial Services

Who is this presentation for?

Engineer / Machine learning researcher




Graphs are a powerful way to represent knowledge. They can represent disparate types of knowledge in one unified structure. Organizations (in fields such as bio-sciences and finance) are starting to amass large knowledge graphs, but lack the machine-learning tools to extract the insights they need from them.

In this presentation, I’ll give an overview of what insights are possible and survey the most popular approaches. I’ll also point out the areas of active research. Finally, I’ll provide thorough online resources and bibliography for the audience to use in their work.

This talk is based on recent articles and talks I’ve worked on with my colleague Andy:

Prerequisite knowledge

Neural networks basics

What you'll learn

How to get started with machine learning on graphs
Photo of David Mack

David Mack


David is a founder and machine learning engineer at, exploring new approaches to machine learning on graphs

Previously he co-founded of SketchDeck, a Y-Combinator backed technology startup providing design as a service. He has a MSci in Mathematics and the Foundations of Computer Science from the University of Oxford and a BA in Computer Science from the University of Cambridge.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)

Contact us

For conference registration information and customer service

For more information on community discounts and trade opportunities with O’Reilly conferences

For information on exhibiting or sponsoring a conference

Contact list

View a complete list of Strata Data Conference contacts