Knowledge Graphs
Supervisors: Dr. Ralf Krestel
Organisation: We will start the seminar as an online event. Please register with the Studienreferat@hpi.uni-potsdam.de before April 9th, 2021. All registered students will receive an email with information about online access (Zoom link).
The introductory, first session is open to all and will take place on Tuesday, April 13th at 09:15 on Zoom.
If more than 9 students remain registered, we will choose randomly.
The slides can be found in the shared folder in the internal area: https://hpi.de/intern/studium/materialien.html under FG Informationssysteme/Masterseminare/KnowledgeGraphs_SS21
This seminar's focus is on knowledge graphs (KG) in general and on three common knowlege graph problems in particular. We will learn about KG construction, KG completion using embeddings, and KG correction based on current state-of-the-art deep learning approaches. In the first half of the semester, each student will read and present one paper solving one of the three tasks. In the second half, the students will work in teams of three to create/complete/correct a knowledge graph. We collaborate with the Wildenstein Plattner Institute in New York, which provides training data, namely a large collection of art-historic documents out of which a KG should be created.
Schedule
Time: 09:15
Location: Campus 2, F-E-06 (later in the semester if possible) and Zoom
| Date | Topic |
|---|---|
| April 13th | Organization & Introduction to Knowlege Graphs (KGs) |
| April 20th | Initial Meeting & Introduction to KG Construction |
| April 27th | 2 Student Presentations |
| May 4th | 1 Student Presentations & Introduction to KG Completion/Embeddings |
| May 11th | 2 Student Presentations |
| May 18th | 1 Student Presentations & Introduction to KG Correction |
| May 25th | 2 Student Presentations |
| June 1st | 1 Student Presentations & Introduction to Project Work |
| July 20th | 3 Team Presentations & Closing of Seminar |
(still updated, subject to change)
Grading
- 50% Paper Presentation
- 50% Team Project
(subject to change)
Prerequisites
- Basic knowledge of machine learning is necessary (What is cross-validation? What is an objective function? What is classification? What are labels? etc.).
- Having prior knowledge about deep learning is an advantage but not required (What is backpropagation? What is a CNN? etc.).
- Having some experience with Python is recommended.