Fairness, Explainability, and Accountability for ML 2019

Fairness, Explainability, and Accountability for Machine Learning

The course is focused on the ethical implications of applying Big Data and ML tools to socially-sensitive domains, and will present a tool-box of technical solutions for addressing these issues. VVZ Information is available here.
Announcements
  • The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the course, will officially fail the course.
  • The files are password protected. To obtain the password you need to be inside the ETH network and click here. To establish a VPN connection click here.

Contact
Lectures and Office Hours
Lectures Wed 9-11 CAB G 59
Office hours Tue 9-11 CAB F 63.2

Syllabus
Date Session 1 Session 2
Wed 20.2. Introduction Sources of Unfairness
Wed 27.2. Statistical Notions of Fairness Individual Notions of Fairness
Wed 6.3. Fairness Mechanisms Tradeoffs and Impossibilities
Wed 13.3. Counterfactual Fairness Long-term Algorithmic Impact
Wed 20.3. Explainability (global methods) Explainability (local methods)
Wed 27.3. Governance and Accountability Misc.
Wed 3.4. Midterm Exam
Wed 10.4. Data Pre-processing Methods Software Tools for Fairness
Wed 17.4. Fair Feature Selection Fairness in Representations
Wed 8.5. Bias in Natural Language Processing Combining Human and Machine Decisions
Wed 15.5. Preference-based Notions of Fairness Welfare and Risk
Wed 22.5. Feedback Loops Intersectionality and Fairness Gerrymandering
Wed 29.5. Fairness for and through Voting Fairness for Ranking and Recommendation Systems

Projects
Information about course projects can be found here. The project-to-team assignments can be found here. The deadline for project reports is June 6th. The LaTeX template for presentation slides can be found here. The LaTeX template for project reports can be found here.

Performance Assessment
The final grade will be computed based on:
  • 30% written mid-term exam
  • 60% project (40% written report + 20% class presentation)
  • 10% participation in class discussions (10%)