Lecturer | Prof. Dr. Markus Strohmaier, Marlene Lutz, Tobias Schumacher |
Course Format | Seminar |
Offering | HWS/ |
Credit Points | 4 ECTS |
Language | English |
Grading | Written report with oral presentations |
Examination date | See schedule below |
Information for Students | The course is limited to 15 participants. Please register centrally via Portal2. |
In this seminar, students perform scientific research, either in the form of a literature review or by conducting a small experiment, or a mixture of both, and prepare a written report about the results. Topics of interest focus around a variety of problems and tasks from the fields of Data-Science, Network Science and Text Mining.
Previous participation in the courses “Network Science” and “Text Analytics” are recommended.
Expertise: Students will acquire a deep understanding of the research topic. He/
Methodological competence: Students will develop methods and skills to find relevant literature for his/
Personal qualification: Students will acquire skills on how to find relevant literature for a research topic, organize a small research task, write a well-structured, concise paper about it and present the results of their work. He/
Deep learning methods have emerged as key tools to represent and infer on data. Yet, there is no one-fits-all solution, and different kinds of data require different modeling approaches to properly meet their characteristics.
In this seminar, we consider neural network models for language and network data, and specific challenges that arise when modelling these kinds of data. Thus, this seminar is split into two blocks: the first examines the responsible use of language models, whereas the second block explores methods for fair network representation learning. In both blocks, we will consider recent studies from top-tier conferences, aiming to gain deep understanding of state-of-the-art approaches for the given deep learning problems.