Hasso-Plattner-Institut
Prof. Dr. Felix Naumann
  
 

Knowledge Graphs

Supervisors: Dr. Ralf Krestel

Organisation: We will start the seminar as an online event. Please register with the Studienreferat(at)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

DateTopic
April 13thOrganization & Introduction to Knowlege Graphs (KGs)
April 20thInitial Meeting & Introduction to KG Construction
April 27th2 Student Presentations
May 4th1 Student Presentations & Introduction to KG Completion/Embeddings
May 11th2 Student Presentations
May 18th1 Student Presentations & Introduction to KG Correction
May 25th2 Student Presentations
June 1st1 Student Presentations & Introduction to Project Work
July 20th3 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.