SM 445: Data and Web Science Seminar (HWS 2023)

The Data and Web Science seminar covers recent topics in data and web science. This term's seminar is for BSc students only and focuses on selected topics in machine learning.

• This seminar is organized by Prof. Dr. Rainer Gemulla and Adrian Kochsiek.
• Available for BSc students (2 SWS, 5 ECTS).
• Prerequisites: BSc courses in CS of terms 1–4 and, in particular, Wifo4

In this seminar, you will

• Read, understand, and explore technical and scientific literature
• Write a concise technical report (10 single-column pages + references)
• Give two oral presentations (3 minutes flash presentation, 15 minutes final presentation)
• Moderate a scientific discussion around the presentation of one of your fellow students
• Review a (draft of a) report of a fellow student

• Register via Portal2 until 04.09.2023.
• Attend the online kickoff meeting on 13.09.2023.
• Work individually throughout the semester according to the seminar schedule.
• Meet your advisor for guidance and feedback.

Register via Portal 2 until Sep 4.

If you are accepted into the seminar, provide at least 4 topic areas ranked by your preference (see below for details) by Sep 10 via email to Adrian Kochsiek. The actual  assignment takes place soon afterwards; we will notify you via email. Our goal is to assign one of your preferred topic areas to you.

You will be assigned a topic area in an active, relevant field of machine learning based your preferences. Your goals in this seminar are

1. Provide a short, concise overview of this topic area (1/3).  A good starting point may be a book chapter, survey paper, or recent research paper. Here you take a birds-eyes view and are expected to discuss the main goals, challenges, and relevance of your topic area. Topic areas are selected at the beginning of the seminar.
2. Present a self-selected topic within this area in more detail (2/3). A good starting point is a recent or highly-influential research paper. Here you dive deep into one particular topic and are expected to discuss and explain the concrete problem statement, concrete solution or contribution, as well as your own thoughts. The actual topic is selected in the first tutor meeting.

You are generally free to propose your topic area of interest. Your area needs to be (i) an active, relevant area in machine learning, (ii) not part of the BSc Wifo (and, in particular, Wifo 4), and (iii) not solely refer to a general architecture (such as RNNs, CNNs, Transformers) or a very narrow subfield. If unsure, ask us upfront.

Some examples of suitable topic areas include:

• pretraining
• optimization for machine learning
• machine learning frameworks
• parallel machine learning
• federated machine learning
• differential privacy in machine learning
• regularization
• few-shot learning
• semi-supervised learning
• reinforcement learning
• (deep) generative modelling
• AutoML
• PAC learning
• multi-task learning
• transfer learning
• weak supervision
• ML in a concrete application area
• explainable machine learning
• fair machine learning

• “Giving Conference Talks”by Prof. Dr. Rainer Gemulla
• “Writing for Computer Science” by Justin Zobel, Springer, 2014