Knowledge Graph Lab

Knowledge Graphs

VU 192.116, 2021S, 2.0h/3.0ECTS

A very warm welcome to "Knowledge Graphs"! You can find the "static" information for the course on this page. The TISS page is now available, and the TUWEL page - which will be our main communication platform - will go online on 01.03.2021. If you have any urgent questions, please email the lecturer Prof. Dr. Emanuel Sallinger (sallinger@dbai.tuwien.ac.at) and the KG Lab team!

MOTIVATION

What are Knowledge Graphs?

Almost every one of us has come into contact with a Knowledge Graph (KG): If we perform a web search, such as the Google search shown in the figure below, we do not only get a list of websites (shown on the left of the figure), but also a panel (highlighted with a yellow border on the right) with information coming from Google's Knowledge Graph.

Beyond Google, the concept of Knowledge Graphs has become - depending on who you ask - the next step in the evolution of how we represent and reason about knowledge, or a shift in how we utilize knowledge in Artificial Intelligence. The answer to the question "What is a Knowledge Graph?" and what we can do with it is of course what this course is all about, but if you are interested to read more about current research on the topic, you can follow the link below.

Course Content

The aim of this is course is to gain a deep understanding of Knowledge Graphs divided into three blocks. An overarching aim of the course is to understand the connections between Knowledge Graphs, Artificial Intelligence, Machine Learning and Data Science.

Representations

Logical and ML-based representations for KGs.

  • KG Embeddings

    Widely-applied, large family of ML models.

  • Logical Knowledge in KGs

    Highly expressive, diverse family of logical models.

  • Graph Neural Networks

    Using the KG structure as a neural network.

  • Data Models

    Overview of data models in different communities.

Systems

Systems to bring KGs into practice.

  • Architectures

    The big picture of building IT architectures for KGs.

  • Scalable Reasoning

    Making use of the knowledge in the KG.

  • KG Creation

    How to create a KG from heterogeneous data?

  • KG Evolution

    How to update, correct and complete a KG?

Applications

Real-world applications of KGs.

  • Real-World Applications

    Overview of diverse applications.

  • Financial KGs

    Concrete applications in finance and economics.

  • Services

    Which service to provide based on KGs?

  • Connections

    ... between KGs, AI, ML and Data Science.

Course Organization

COURSE ORGANIZATION

A Quick Overview

All topics will be covered by lectures offered via distance learning. Assessment is by a mini-project. The procedure is in three simple steps:

  • one-page summary proposing a mini-project by you
  • feedback on the proposal
  • submission of the final mini-project report ("portfolio")

This will be supported by discussions and feedback throughout the course.

For more details on the organization of the course, including examples for mini-project ideas, exact ECTS distribution, curriculum assignment, etc., please see the below link:

More questions?


Email the lecturer Prof. Dr. Emanuel Sallinger (sallinger@dbai.tuwien.ac.at) and the KG Lab team!

About the Knowledge Graph Lab at TU Wien

The Knowledge Graph Lab at TU Wien is part of the Database and Artificial Intelligence (DBAI) group at the Institute of Logic and Computation of the Faculty of Informatics. It is funded by the Vienna Science and Technology Fund (WWTF) under the Vienna Research Group scheme - "Vienna Research Group on Scalable Reasoning in Knowledge Graphs" (VRG18-013).

TU Informatics
DBAI
WWTF
DeepReason.ai

We would like to thank DeepReason.ai, a spin-out of the University of Oxford, for the joint development of the Vadalog Knowledge Graph Management System and the collaboration.

Contact

For inquiries please contact Prof. Dr. Emanuel Sallinger, head of the Knowledge Graph Lab at TU Wien, at <sallinger@dbai.tuwien.ac.at>.