After successful completion of the course, students are able to demonstrate a deep understand of Knowledge Graphs (more details further below!)
Welcome to Knowledge Graphs 2023!
This semester, we are going to offer a "best of both worlds" edition between virtual and physical participation:
- You are going to be able to partcipiate fully virtually if you like - no presence needed. Watch the videos whenever you like.
- We will offer four face-to-face live units (completely optional).
Live Units
You can find the dates and times in the corresponding TISS section. If you are blocked for some of them, no problem, they are optional. Some further facts:
- Each live unit is just 2 hours, so the total time investment in the live units is 8 hours.
- These are especially for those of you who like physical presence, and see this as motivating - we encourage you to participate in them, as it is always nice to meet face-to-face to stay motivated.
- These will complement the virtual parts - we will go through some of the core points, see examples that hopefully motivate you, and can answer questions.
The theme of them will be:
- Live 1 - "Kick-Off Meeting" / Vorbesprechung
- Live 2 - "Groundbreaking Knowledge Graph Projects - Get your final ideas for your one pagers"
- Live 3 - "Let's Talk About AI Techniques"
- Live 4 - "Bringing It All Together"
More
All other details will follow via TUWEL and/or in the first live unit (if you participate).
If you want to join the course, please do not forget to register via TISS, so that you get all updates and will be able to access TUWEL when the course launches in 2023S!
For those of you who join us, see you all soon!
In TISS all details are presented linearly on one page.
Learning outcomes are divided into three main blocks:
- Representations of Knowledge Graphs
(logic- and ML-based)
- Systems for Knowledge Graphs
(scalablility and reasoning)
- Applications of Knowledge Graphs
(real-world enterprise AI)
An overarching aim of the course is to understand the connections between Knowledge Graphs (KGs), Artificial Intelligence (AI), Machine Learning (ML), Deep Learning and Data Science.
Learning outcomes (LOs) are structured into exactly these three blocks. A particular focus is of gaining a broad understanding of all of the following learning outcomes, coming from throughout the database, semantic web, machine learning and data science communities.
Representations
The aim in this part is to understand and apply the predominant representations of knowledge and data in Knowledge Graphs.
- (LO1) Understand and apply Knowledge Graph Embeddings
- (LO2) Understand and apply logical knowledge in KGs
- (LO3) Understand and apply Graph Neural Networks
- (LO4) Compare different Knowledge Graph data models from the database, semantic web, machine learning and data science communities.
![Knowledge Graph Representations](https://kg.dbai.tuwien.ac.at/kg-course/tiss/kg-2-representations.png)
This, crucially, includes the connections between using these types of knowledge in one Knowledge Graph.
Systems
The aim in this part is to be able to design and apply systems that manage Knowledge Graphs.
- (LO5) Design and implement architectures of a Knowledge Graph
- (LO6) Describe and apply scalable reasoning methods in Knowledge Graphs
- (LO7) Apply a system to create a Knowledge Graph
- (LO8) Apply a system to evolve a Knowledge Graph
![Knowledge Graph Systems](https://kg.dbai.tuwien.ac.at/kg-course/tiss/kg-3-systems.png)
The latter two learning outcomes (together with LO11) provide a typical life-cycle of Knowledge Graphs: getting data into a KG, i.e., creating it (LO6), evolving a KG into a new one (LO7) and getting data out of a KG by providing services based on it (L11). Note that the term “life-cycle” is used loosely here, as in many Knowledge Graphs, providing applications is not necessarily the end of the life-cycle, but part of an on-going activity.
![Knowledge Graph Lifecycle](https://kg.dbai.tuwien.ac.at/kg-course/tiss/kg-4-lifecycle.png)
Applications
The aim of this part is to understand and design applications of Knowledge Graphs.
- (LO9) Describe and design real-world applications of Knowledge Graphs
- (LO10) Describe financial Knowledge Graph applications
- (LO11) Apply a system to provide services through a Knowledge Graph
- (LO12) Describe the connections between Knowledge Graphs (KGs), Machine Learning (ML) and Artificial Intelligence (AI)
![Knowledge Graph Applications](https://kg.dbai.tuwien.ac.at/kg-course/tiss/kg-5-applications.png)
A particular focus here is getting a holistic understanding of the topics including their connections.
To support a diversity of learning types, the course has multiple options in terms of how you want to complete it.
In terms of timing:
- "Early Bird" (complete before the start of the "exam season", i.e., mid June)
- Standard (complete within the semester)
- Extended (complete by end of the summer break)
You can freely choose between them. Of course, only one has to be completed to successfully complete the course. In terms of virtual vs physical, due to the high interest last year, we have opened up the live part and will offer (optional)
- Live Units (In-person Learning; blocked setting)
The live units will be held blocked and may be subject to COVID regulations and limitations of lecture rooms. They are really here to communicate and keep you motivated - so they have no effect on marking - but are designed to get to the core points more quickly and support your completion of the portfolio.
Activities
Supporting a diversity of learners, and in line with education literature that suggests inclusive design and a diversity of methods rather than individual intervention, learning is centred around covering all LOs form multiple perspectives.
- Lectures. This is particularly helpful to learners accessible to the "transmission" learning perspective. This is not limited to classical frontal lecturing, but includes situations where the entire class is participating in joint activities such as via virtual whiteboards (as defined by the individual session plan). Such situations are designed to address the typical challenges of frontal lecturing, in particular student engagement. This stream covers all LOs, but with a limited depth on those that require active practice.
- Project. This is particularly helpful to learners accessible to the "apprenticeship" learning perspective. This includes what education literature on active learning suggests on presenting "messy" real problems. Here the concept is very simple: in one consistent project, the learner goes through all LOs.
- Project Portfolio. Again, the learner goes through all LOs, and by having to assemble a project portfolio (i.e., report highlighting the achieved results with respect to the LOs) facilitates reflecting on the own learning progress. This enables self-regulated learning.
Further details on the project portfolio can be found under "examination modalities".
Summative assessment is by one item: the project portfolio. The portfolio was already briefly mentioned in the "teaching methods" section. In particular, it:
- gives a clear, transparent basis for the achieved marks, and puts control of demonstrating the achieved learning outcomes into one's own hands.
- allows diversity in how to demonstrate the learning outcomes: while a typical way to demonstrate that would be a practical project portfolio, learners who are pursuing a theoretical direction will be able to demonstrate that through a theoretical project portfolio.
- allows for self-regulated learning: while the portfolio is the single assessment item, it is the witness of a longer learning process, and can be created - using the principle of "patchwork" text - throughout the learning process, or in one block at the end, depending on the learning type.
The following is a (non-exhaustive) list of examples of what can make a good project and portfolio topic:
- Application-oriented: Portfolio on creating a financial Knowledge Graph, based on public data in Austria combined with EU-level open data.
- System-oriented: Portfolio on a KG used for scalable reasoning using one ML-technique and a logic-based technique.
- Foundations-oriented: Portfolio on complexity of KG processing and reasoning in an, e.g., databases or ML-based KG framework.
- State-of-the-art-oriented: Portfolio on the state-of-the-art of Graph Neural Network-based reasoning that incorporates domain knowledge for a chosen domain, and shows how the techniques could be applied.
Each portfolio will have a particular focus, but needs to put it in the context of the other learning outcomes. E.g., while not every portfolio will apply KG Embeddings based models, it should put the covered topics in the context, to demonstrate meeting the learning outcomes.
The procedure is in three simple steps:
- one-page summary proposing a portfolio project by the learner
- formative feedback on the proposal to the learner
- submission of the final portfolio
This will be supported by discussions and feedback throughout the course.
Grading is according to the following principles:
- G4: Showing basic proficiency in at least 6 learning outcomes.
- B3: Showing basic proficience in at least 10 learning outcomes.
- U2: As above, and exceeding the threshold in at least 1 learning outcome.
- S1: As above, and exceeding the threshold in at least 2 learning outcomes.
That is, it is not necessary for each portfolio to go beyond basic proficiency in all learning outcomes, but perfectly fine to excel in a selection of them.
The curricula information is currently being updated. Until this is the case we provide here the following information:
In Which Curricula is the Course?
- E 066 931 Logic and Computation:
Module "Knowledge Representation and Artificial Intelligence"
- E 066 936 Medical Informatics:
Module "Information Processing" ("Informationsverarbeitung")
- E 066 937 Software Engineering & Internet Computing:
Module "Information Systems" ("Informationssysteme")
- E 066 926 Business Informatics:
Module "ISE/EXT – Information Systems Engineering Extension"
- E 066 645 Data Science:
Module "VAST/EX – Visual Analytics and Semantic Technologies - Extension"