Navigation auf


Department of Informatics

IfI Summer School 2021

The 2021 IfI Summer School is a week-long event for PhD students and research assistants in informatics and related fields, where invited experts teach a number of different topics in day-long courses.

Dates and Location

The summer school will take place June 28 - July 2, 2021 at the University of Zurich, Department of Informatics.
Due to the current situation with the Corona pandemic the IfI Summer School 2021 will be operated digitally via Zoom.

Courses will be held from 9 a.m. - 5 p.m. (check-in starts at 8:45) with coffee and lunch breaks. 
Exception: Monday June 28 course, this course will be held from 1 p.m. - approx. 7 p.m with coffee breaks.


List of Courses

Day Course Instructor ECTS credits
MON, June 28

Algorithms for Incentive-Aware Learning 

Chara Podimata 0.5 Doctoral
TUE, June 29 Scientific Document Processing: Terminology, Citations and Creativity Prof. Dr. Simone Teufel 0.5 Doctoral
WED, June 30 Inequalities in Social Networks Prof. Dr. Markus Strohmaier 0.5 Doctoral
WED, June 30 Research Philosophy Prof. Dr. Alexander Prescott-Couch 0.5 Methodology
THU, July 1 Walking the Talk – Building Conversational Interfaces Dr. ir. Ujwal Gadiraju 0.5 Doctoral
FRI, July 2 Certified Fair, Robust and Safe Deep Learning: Techniques and Tools Prof. Dr. Martin Vechev 0.5 Doctoral

Please note: All courses cover a full day. You need to attend the full day to get the 0.5 ECTS credits!

Please make sure your register for each course you want to attend separately.


Daily schedule (subject to change as needed by instructors)

08:45 - 09:00 Check-in
09:00 - 10:15 Instruction
10:15 - 10:45 Coffee break
10:45 - 12:00 Instruction
12:00 - 13:00 Lunch break
13:00 - 15:00 Instruction
15:00 - 15:30 Coffee break
15:30 - 17:00 Instruction

Please note: Monday June 28 course will be held with a specific daily schedule: 1 p.m. until approx. 7 p.m.



The Summer School is primarily targeted towards doctoral students in computer science and related fields from the University of Zurich as well as other universities. Registration is free for IfI  and CL research assistants, IfI and CL doctoral students, and IfI and CL postdocs. For all other UZH participants, fees are 50 CHF per course day. For all other participants, fees are 100 CHF per course day. The fee can only be paid by credit card, PostFinance or TWINT using the link below. 

  • Registration is closed.

Contact: Karin Sigg

ECTS Credits

For UZH students, you can find the ECTS credit awarded by each course in the overview above. Non-IfI students who would like to acquire credits, need to talk with the person who is in charge of credit transferring at their home university first and find out if the ECTS credits awarded by IfI at UZH are accepted/recognized.

Courses and Instructors

June 28

Algorithms for Incentive-Aware Learning

Course Description

Machine Learning (ML) algorithms are increasingly being used for making highly consequential decisions. Before these algorithms are deployed, they are carefully vetted against stochastic and adversarial attacks. But what if these models of attacks fail to fully capture the goals and the desires of real-life “attackers”, who are strategic and instead of wishing to sabotage the ML algorithm entirely, they wish to “game” it in order to rip the benefits for themselves as much as possible? In this course we will study three settings where this interplay of the ML algorithm with strategic agents is crucial: Stackelberg security games, strategic classification, and dynamic pricing. We will review the tools used to study these settings including both Algorithmic Game Theory (like Nash and Stackelberg Equilibrium analysis) and Machine Learning (like online learning and learning in the presence of limited corruptions) and will highlight some key recent advances. Throughout the course, we will outline open directions for future research.

Instructor Chara Podimata
Short Bio Chara Podimata is a fifth-year PhD student in the EconCS group at Harvard, where she is advised by Yiling Chen. Her research interests lie in the intersection of Theoretical Computer Science, Economics, and Machine Learning and specifically on learning in the presence of strategic agents, online learning, and mechanism design. She has been twice an intern at MSR NYC mentored by Jennifer Wortman Vaughan and Alex Slivkins respectively. She is currently an intern at Google Research NYC mentored by Renato Paes Leme. She is a recipient of the Microsoft Dissertation Grant.

June 29


Scientific Document Processing: Terminology, Citations and Creativity

Course Description

Scientific writing contains valuable information, which comes in the form of a description of the end result of months of research. The scientific text also explains the setting of this research in the existing universe of scientific knowledge. It is a complex and rich construction. Recently, much progress has been made in extracting and using various aspects of this valuable research information from the text. This workshop will provide an overview of various NLP methods which annotate, extract and evaluate these aspects. We will look at terminology detection and extraction, citation analysis, rhetorical function classification and summarization, with a final excursion to scientific question answering via reasoning, and some attempts of determining creativity in research. The course will include some hands-on work in annotation which illustrates some of the particular difficulties in some of these types of processing. 

Instructor  Prof. Dr. Simone Teufel
Short Bio Simone Teufel is Professor of Language and Information at the Department of Computer Science and Technology at Cambridge University. After achieving her first degree in Computer Science from the University of Stuttgart, she did her PhD research at the Cognitive Science in Edinburgh University, on the topic of scientific rhetoric detection and summarization. She spent 2 years as postdoc at Columbia University working on medical information extraction. Since 2001, she has been a permanent member of staff at the Department of Computer Science and Technology (formerly Computer Laboratory). She is also a frequent collaborator at the Tokyo Institute of Technology. Her research interests include argumentation mining, reasoning, discourse processing, and all aspects of human evaluation of NLP tasks.

June 30


Inequalities in Social Networks

Course Description

The workshop will 1) give an introduction to recent work in the area of Computational Social Science, what it is and what kinds of challenges it aims to tackle and 2) highlight issues related to inequalities in social networks. Overall, the workshop will motivate and exemplify new research endeveaors on the intersection between computational and social sciences. Students shall gain a deeper understanding of social issues related to social systems, and how to measure, analyze and - potentially - address them.

Instructor Prof. Dr. Markus Strohmaier
Short Bio

Markus Strohmaier is the Professor for Methods and Theories of Computational Social Sciences and Humanities at RWTH Aachen University (Germany), the Scientific Coordinator for Digital Behavioral Data at GESIS - Leibniz Institute for the Social Sciences and an external faculty member at the Complexity Science Hub Vienna. Previously, he was a Post-Doc at the University of Toronto (Canada), an Assistant Professor at Graz University of Technology (Austria), a visiting scientist at (XEROX) Parc (USA), a Visiting Assistant Professor at Stanford University (USA) and the founder and scientific director of the department for Computational Social Science at GESIS (Germany). He is interested in applying and developing computational techniques to research challenges on the intersection between computer science and the social sciences / humanities.

June 30

Research Philosophy

Course Description The Research Course in Philosophy will introduce students to fundamental philosophical issues about scientific research. We will focus on four questions:  
What makes inquiry “scientific”?  
How should we understand crucial scientific concepts such as “causation” and “explanation”?  
How can abstract and idealized models help us understand the world even when many assumptions made within these models are false?  
What role, if any, should values play in scientific investigation and hypothesis-testing?  
In the process of thinking about these particular questions, we will also discuss how to reason philosophically about abstract conceptual questions and questions of value. Do such questions really have answers? Why do the answers matter, and how should we go about trying to figure them out if they do?
Instructor Prof. Dr. Alexander Prescott-Couch
Short Bio Alexander Prescott-Couch is an Associate Professor at the University of Oxford and a Fellow of Lincoln College. Before coming to Oxford, he completed his PhD at Harvard University and held post-doctoral positions at the University of Chicago and MIT. His research focuses on the philosophy of social science, political philosophy, and the history of social theory. His work has been published in Noûs, The Journal of Political Philosophy, and The Journal of Nietzsche Studies. 

July 1


Walking the Talk – Building Conversational Interfaces

Course Description Conversational interfaces have been argued to have advantages over traditional GUIs due to having a more human-like interaction. The rise in popularity of conversational agents has enabled humans to interact with machines more naturally. There is a growing familiarity among people with conversational interactions mediated by technology due to the widespread use of mobile devices and messaging services such as WhatsApp, WeChat, and Telegram. Today, over half the population on our planet has access to the Internet with ever-lowering barriers of accessibility. This course will showcase the benefits of employing novel conversational interfaces in the domains of Health and Wellbeing, Information Retrieval, and Crowd Computing. We will discuss the potential of conversational interfaces in facilitating and mediating the interactions of people with AI systems. The course will include an interactive, hands-on component to provide participants with an opportunity to build conversational interfaces.
Instructor  Dr. ir. Ujwal Gadiraju
Short Bio Ujwal Gadiraju is an Assistant Professor at the Web Information Systems (WIS) group of the Software Technology department at Delft University of Technology, the Netherlands. He is a Director of the Delft AI ‘Design@Scale’ Lab, which focuses on Human-AI collaboration to design solutions for complex social problems. Ujwal leads a research line on Crowd Computing and Human-Centered AI at the WIS group. He is a Distinguished Speaker of the ACM. Ujwal’s research lies at the intersection of Human-Computer Interaction and Information Retrieval. He received a Best Paper Honorable Mention award at the ACM CSCW 2020 conference, advised and co-authored work that won a Best Student Paper award at AAAI HCOMP 2020, and the Douglas Engelbart Best Paper award at the ACM HT2017 conference. Before joining TU Delft, he worked at the L3S Research Center in Hannover, Germany as a postdoctoral researcher between 2017-2020. In 2017, Ujwal received a PhD degree with a summa cum laude from the Leibniz University of Hannover. For more information about Ujwal’s research, projects, professional service, and other news visit 

July 2

Certified Fair, Robust and Safe Deep Learning: Techniques and Tools

Course Description In this lecture I will cover some of the latest techniques for creating certified deep learning models, ones we can provably trust to satisfy a given property (e.g., robustness, fairness, safety). Concretely, we will cover techniques such as convex relaxations, verification and certified training as well as enforcing background priors. In the process I will also outline existing tools as well as open research questions.
Instructor Prof. Dr. Martin Vechev
Short Bio

Martin Vechev is an Associate Professor of Computer Science at ETH Zurich where he leads the SRI lab ( His research interests span programming languages, machine learning and probabilistic reasoning. He co-founded 3 ETH spin-offs: DeepCode, ChainSecurity and LatticeFlow, the first two acquired and the latest one focusing on creating new tools that help build more reliable and trustworthy AI models.

Weiterführende Informationen


Teaser text