CS 707: Data and Web Science Seminar (FSS 2020)

The Data and Web Science seminar covers recent topics in data and web science. This term, the seminar focuses on Fairness in Machine Learning.

• This seminar is organized by Daniel Ruffinelli and Prof. Dr. Rainer Gemulla.
• Available for Master students (2 SWS, 4 ECTS). If you are a Bachelor student and want to take this seminar (2 SWS, 5 ECTS), please contact Prof. Gemulla.
• Prerequisites: solid background in machine learning
• The maximum number of participants is 10 students

In this seminar, you will

• Read, understand, and explore scientific literature
• Summarize a current research topic in a concise report (10 single-column pages + references)
• Give two presentations about your topic (3 minutes flash presentation, 15 minutes final presentation)
• Moderate a scientific discussion about the topic of one of your fellow students
• Provide feedback to a report and to a presentation of a fellow student

• Register as described below.
• Attend the kickoff meeting on Feb 19.
• Work individually throughout the semester according to the seminar schedule (PDF, 170 kB).
• Meet your advisor for guidance and feedback.

Register via Portal 2 until 10 February.

If you are accepted into the seminar, provide at least 4 topics of your preference (your own and/or example topics; see below) by 16 February via email to Daniel Ruffinelli. The actual topic assignment takes place soon afterwards; we will notify you via email. Our goal is to assign one of your preferred topics to you.

Each student works on a topic within the area of the seminar along with a accompanying reference paper. Your presentation and report should explore the topic with an emphasis on the reference paper, but not just the reference paper.

We strongly encourage you to explore the available literature and suggest a topic and reference paper of your own choice. Reference papers should be strong papers from a major venue; contact us if you are unsure. The following resources may help during exploration:

• Mehrabi et al., 2019. A survey on bias and fairness in machine learning (draft)
• Barocas et al., 2019. Fairness and machine learning (draft)
• Barocas and Hardt, 2017. NIPS tutorial: Fairness in machine learning (includes video)

We provide example topics and reference papers below.

1. Classification
   Learning Fair Representations (PDF)
   Zemel et al.
   In ICML 2013
2. Text classification
   Measuring and Mitigating Unintended Bias in Text Classification
   Dixon et al.
   In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society
3. Adversarial Learning
   Mitigating Unwanted Biases with Adversarial Learning (PDF)
   Zhang et al.
   In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society
4. Measuring fairness in classification
   Equality of Opportunity in Supervised Learning (PDF)
   Hardt et al.
   In NIPS 2016
5. Variational Autoencoders
   The Variational Fair Autoencoder (PDF)
   Louizos et al.
   In ICLR 2016
6. Fairness in classification via dataset constraints
   Satisfying Real-world Goals with Dataset Constraints (PDF)
   Goh et al.
   In NIPS 2016
7. Word embeddings
   Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings (PDF)
   Bolukbasi et al.
   In NIPS 2016
8. Clustering
   Proportionally Fair Clustering (PDF)
   Chen et al.
   In ICML 2019
9. Computer vision
   Towards fairer datasets: filtering and balancing the distribution of the people subtree in the ImageNet hierarchy
   Chen et al.
   In ICML 2019

• “Giving Conference Talks” (PDF, 1 MB) by Prof. Dr. Rainer Gemulla
• “Writing for Computer Science” by Justin Zobel