Description

Graph ML - The next level of Machine Learning; Learn how to use it and also when not to!

This Masterclass focuses on why Graphs have become one of the biggest trends in Machine Learning. Graph Machine Learning based on graph analytic algorithms is driving significant improvements in Fraud/Anomaly Detection, Ranking (Page Rank), Recommendation Engines (collaborative filtering), text summarization, and other NLP tasks.

The Masterclass covers Graph Analytic Algorithms and their applications and the more novel–but equally exciting–field of Graph Machine Learning, including topics such as Graph Embeddings and Graph Neural Networks and applications of Graph Machine Learning.

The Masterclass is hands-on using jupyter notebooks, so there is no need to pre-install software. However, it is important to verify that your network has access to Colab.

Key Topics

• Hands-on Experience and best practices on
  • Graph Modeling
  • Graph Analytics
  • State of the Art Graph Machine Learning
• Tradeoffs between different Options in respect to performance and complexity

Target Audience

• Data Scientist/Analyst
• Data Architects
• Engineers interested in Data Science
• Scientists interested  in Data Science
• Architects/Data Solution Specialists

Goals

• Understand the value of Graph Data and its applications and best practices in Analytics and Machine Learning.

Session outline:

• Introduction to Graph
• Graph Use Cases
• Graph Modeling & Storage
• Graph Analytics
• Graph Machine Learning
  • Embeddings
  • Graph Neural Networks
• Conclusion
  • Additional resources

Format

• The class will be a mix of interactive lectures followed by hands-on exercises for each part.
• These exercises will be based on Colab backed jupyter notebooks.
• We will summarize everything we learned by working on a final project in small teams.

Level

Intermediate - Advanced

Prerequisite Knowledge

Prior exposure to Graph Databases or Machine Learning is helpful but not required.

You need an access pass to attend this session: Diversity Access Pass or Full Access Pass apply