Course Abstract

Training duration : 90 minutes

Machine Learning and Graph Processing (e.g., Knowledge Graphs) have been two of the main trends over the past years. Many powerful Machine Learning algorithms are based on graphs, e.g., Page Rank (Pregel), Recommendation Engines (collaborative filtering), text summarization and other NLP tasks. There are even more applications once we consider data pre-processing and feature engineering which are both vital tasks in Machine Learning Pipelines. In this course we will consider the symbiosis of graphs and Machine Learning.

DIFFICULTY LEVEL: INTERMEDIATE

Learning Objectives

  • nderstand Graph-based Feature Engineering and Graph Algorithms

  • Understand Graph Embeddings and Graph Neural Networks

  • Text length of individual points can be shorter or longer depending on your needs

Instructor

Instructor Bio:

Jörg Schad, PhD

Head Of Engineering and Machine Learning | ArangoDB

Course Outline

Module 1: Graph-based Feature Engineering and Graph Algorithms 

- Popular graph algorithm 

- Value for feature engineering for Machine Learning models 

Module 2: Graph Embeddings and Graph Neural Networks

- Utilizing graphs as input to Neural Networks In this part 

- Different Embedding strategies 

- The field of Graph Neural Networks Module 

3: Graph-based Machine Learning Metadata

- Value of high quality and quantity for building high-quality machine learning models 

- Operating a production-grade machine learning pipeline metadata 

- Leveraging graphs to capture metadata and provenance information of machine learning ecosystem.

Background knowledge

  • This course is for current and aspiring Data Scientists, Machine Learning Engineers and Graph Theory Practitioners

  • nowledge of following tools and concepts is useful:

  • Jupyter/Colab notebook

  • Hosted Databases

  • Machine Learning Frameworks

Real-world applications

  • Graph powered machine learning is used IoT applications generating continuous stream of data

  • Graph ML has various applications in telecom, supply chain and logistics industries

  • Graph models are being increasingly deployed for credit-card fraud detections