Graph School

Course/Event Essentials

Event/Course Start
Event/Course End
Event/Course Format
Online
Blended (mixture of live and self-paced)
Primary Event/Course URL
https://indico.truba.gov.tr/e/cizgeokul…

Venue Information

Country: Turkey
Venue Details: Click here

Training Content and Scope

Scientific Domain
Computer sciences, Computer Engineering, Electrical Engineering, Telecommunications
Technical Domain
Data science and high performance data analytics (HPDA)
Level of Instruction
Beginner
Intermediate
Sector of the Target Audience
Research and Academia
HPC Profile of Target Audience
Data Scientists
Language of Instruction
Turkish

Other Information

Organiser
NCC Turkey
Supporting Project(s)
EuroCC/CASTIEL
Event/Course Description

Overview and Description:

Graphs are powerful combinatorial data structures that can model real-life data and the relationships among the entities inside the data. These graph models and representations are commonly used in a variety of domains, including social networks, recommender systems, and biological systems. Some say “if you torture the data long enough, they will confess”. With graphs, you do not need to be cruel. If you know how to use them, they will tell you a lot. As a part of the EuroCC project, this four-day Graph School is designed to make people learn more about graphs, why to use them, and how to use them. The topics covered in this lecture are:

  • Introduction to Graphs
  • Network Science
  • Spectral Graph Theory
  • Graph Signal Processing
  • Graph Embeddings
  • Graph Databases
  • Graphs for NLP
  • Graph Neural Networks
  • Graph Algorithms

Target audience:

All data scientists, machine learning, deep learning enthusiasts, and experts. 

Prerequisites:

Although the school covers the preliminaries as much as possible, for some lectures, familiarity with linear algebra concepts, e.g., eigenvalues and eigenvectors and matrix decomposition etc., can be useful. 

Workflow:

This is a 4-day school where each day has two sessions. There is no hardware or HPC connection required. The presentation materials and the practical exercises will be shared after the course for the students to review and practice on their computers. This year, due to the COVID-19 pandemic, the school was online; but it can be physical to be physical if it is possible. 

Learning outcomes:

At the end of the course, the students will learn:

  • what is a graph and what graph algorithms can be used for,
  • how network science can help us on practical problems and areas such as social sciences,
  • what is a graph database and how one can be used for NLP tasks,
  • what embedding a graph means and how it is helpful to perform ML tasks on relational data,
  • what are Knowledge Graphs, Graph Neural Networks, and Graph Signal Processing and how they are used for in practice?