Seminar Assignment Winter 2021/2022
The central registration for all computer science seminars will open on September 14th.
This system is used to distribute students among the available actual seminars. To register for any of the other seminars that are offered by the computer science department, you have to register here until October 19th 23:59 CET. You can select which seminar you would like to take, and will then be automatically assigned to one of them on October 22nd.
Please note the following:
The assignment will be automatically performed by a constraint solver on October 22nd. You will be added to the respective seminars automatically and be notified about this shortly thereafter. Please note that the assignment cannot be optimal for all students if you drop the assigned seminar, i.e., make only serious choices to avoid penalty to others.
The development of autonomous systems in areas such as industry production, autonomous vehicles, and conversational soft-bots has gained substantial momentum. Most of these systems are designed to work hand-in-hand with humans, like cobots interact with other worker, autonomous cars with their drivers, and retail store bots with staff. The field of AI that we are dealing with in this seminar is human-machine interaction. More specifically, we present concepts and techniques for creating interfaces to autonomous systems that adapt to the user and the situation, learning from user feedback and previous experience, as well as explaining its behavior, such as when the system transfers control to the human. Therefore, this seminar will also cover aspects of applied machine learning in selected domains.
Aside from learning about relevant concepts, participants will work in small groups on a practical project and implementation that demonstrates adaptive behavior based on learned data. Most of these projects also connect to a particular application domain.
More information, as well as the list of available topics / projects, can be found on the seminar website:
Requirements: For the practical projects, programming skills and basic experience in Machine Learning are required.
The course will provide an overview of recent research in Adversarial Reinforcement Learning (RL). Research papers covered in the course will showcase the landscape of attacks on RL agents and the optimal attack strategies, which is crucial for understanding security threats against the deployed systems. In particular, the research papers will cover optimal attack strategies for test-time, training-time, and backdoor attacks on RL agents. After this course, the participants will gain a better perspective of important problems for developing robust and secure algorithms in sequential decision-making settings.
The course schedule is as follows:
(1) Writeups: Each student will be assigned a total of 6 research papers. Students will have to write a short report for each paper. These reports will be due during the semester, roughly 2 reports per month.
(2) Presentation: At the end of the semester, students will give a 20 mins presentation for one of the papers.
This course is offered as a block seminar, and there will be no weekly classes. We will schedule designated office hours where students can receive feedback on their reports and presentation slides.
Requirements: There are no formal requirements, however, please note the following points:
(1) Preference will be given to students who have already taken courses covering topics such as machine learning, artificial intelligence, reinforcement learning, and system security.
(2) We are requesting you to provide a short motivation letter (about 5-10 lines) explaining the reasons why you are interested in taking this seminar. Importantly, you should mention the relevant courses that you have taken along with your grades. Please provide this information in the text box below.
Causality and ethical ML are two mostly disjoint fields in machine learning. Recently, their intersection is attracting increasing attention as models are deployed for consequential decision-making domains. However, most existing literature only sporadically explores this intersection. The aim of this seminar is to bring these efforts together to open a channel of discussion and potential investigations to fill the gaps. Specifically, the seminar focuses on investigating progress in the fields of fairness, explainability and robustness in ML through a causal lens.
Every enrolled student will need to give a talk about the selected paper, participate in at least one discussion panel, and deliver 3 single-page summaries corresponding to the 3 blocks covered in the course.
The seminar will take place weekly (most likely) on Wednesdays between 4-6pm in an online manner. Attendance to weekly meetings is mandatory.
First lecture will take place on October 27th. First two lectures will provide an overview of causality and will be open to all seminar applicants.
For more information, please visit: https://sites.google.com/view/uds-causethical-ml-seminar
Requirements: This seminar aims primarily at master students in Computer Science or related fields, who have prior knowledge of Machine Learning. Ideally participants would have already participated in one or several courses related to machine learning, e.g., Machine Learning, Elements of Machine Learning, Probabilistic Machine learning, Topics in Algorithmic Data Analysis, etc.
We will discuss advanced topics in complexity theory. This seminar builds on the core lecture "Complexity Theory".
This will be a block course during the semester break. Exact dates will be discussed with the participants.
Requirements: Core lecture "Complexity Theory" or equivalent
At the core of many intelligent systems are computational models of the user. They are used to predict users' behavior, their perception of an interface, their intention or interests, and many more. This seminar will introduce students to how such models are developed using computational methods.
Every week we will hear about state-of-the-art research that applies methods from machine learning, optimization, bayesian theory, or other fields to develop predictive or descriptive user models. We will learn how these are applied to improve the user's interaction with a computing system or to enable entirely new ways to interact. In discussing these research papers, students will take on different roles, acting as presenter, historian, journalist or PhD student. See the seminar page for more details: https://cix.cs.uni-saarland.de/?page_id=312
Requirements: The seminar targets Master students. Previous experience in machine learning, data analysis, or optimization is beneficial to follow the papers but not required.
This seminar provides an opportunity to deepen some of the material discussed in "Algorithms for Sequence Analysis". Topics will be selected from the current and recent research literature (papers in English). Examples could be: Suffix array construction algorithms, practical range minimum query implementations, practical rank and select implementations, the wavelet matrix (as an alternative to the wavelet tree), optimal pattern search with compressed texts/BWTs, analysis of actual DNA read-mappers, alignment-free methods and applications to metagenomics and human diseases, hashing algorithms for k-mers. You can also suggest a different research paper that you find interesting and would like to present (the general topic has to be on biological sequence analysis).
Requirements: - You need to be familiar with the material of the course "Algorithms for Sequence Analysis".
- You will receive a research paper at the beginning of the semester.
- You have several weeks to become familiar with the material, get consultation by the instructor, and prepare a written summary. The summary should focus on the methodological parts of the work, and less on the evaluation or results.
- The summary will be read and commented, and may need to be revised.
- Once the summary is accepted, you present the research work in a talk of approximately 45 minutes, including questions and discussion. The presentations will be held as a block seminar.
The focus of this seminar is on recent advances in the areas of software security, network security, privacy, reverse engineering, and similar topics in systems security. Students are expected to independently investigate a narrowly defined topic, typically based on a recent scientific paper. Students are expected to write a text summarizing their findings and prepare a presentation on the topic. The text should be 15 pages long, while the presentation should be about 20 minutes long. This will be complemented by a discussion on the topic.
The seminar is organized similar to a scientific conference. In addition to writing a summary of a particular topic, students also learn about the peer-review process: An important aspect of the seminar is constructive feedback on other students' reports, e.g., in the form of suggestions on how to improve the writing and presentation. Students should then also use this feedback to improve their own text. The seminar will take place at the end of the semester as part of a block seminar, there will be no weekly classes.
There will be a kick-off meeting in the second week of the semester (October 27, 14:00 o'clock via Zoom), where the list of topics will be presented and assigned. For a timeline, including the list of topics, please see https://cms.cispa.saarland/syssecseminar21/
Requirements: Previous knowledge in systems and network security is helpful, students should for example know important vulnerability classes such as stack- and heap-based buffer overflows.
Digital signatures are a basic cryptographic building block that ensures authenticity (who signed) and integrity (what is signed) of messages.
In this seminar, we will learn about different types of digital signatures including not only standard RSA and ECDSA signature schemes but also recent schemes secure against quantum adversaries.
We will also take a look at signature schemes that relax the authenticity and integrity properties to increase the privacy of users and/or message like e.g.:
- ring signatures used in the Monero cryptocurrency,
- pseudonymous signatures used in the German eID, and
- blind signatures used in e-Cash.
Each week we will discuss papers which will be presented by assigned students.
All students are required to read the papers carefully and prepare a list of questions for discussion.
The kick-off meeting will be during the first week of lectures. The seminar will be held in English.
Requirements: A basic understanding of cryptographic primitives such as encryption, signatures, and hash functions is required.
Das Seminar eJustice und Datenschutz ist ein interdisziplinäres Seminar für Informatiker und Juristen.
Ablauf des Seminars:
Studierende erhalten während der Vorbesprechung ein Thema und müssen eine Seminararbeit hierzu anfertigen. Vor der Abgabe der fertigen Seminararbeit ist die Einreichung eines Abstracts vorgeschrieben. Nach der Abgabe des Abstracts kann bei Bedarf bei den Betreuern Feedback zu diesem eingeholt werden. Danach ist die Abgabe eines „Preprints“ der Seminararbeit erforderlich. Dies ist ein Vorabgabe der finalen Seminararbeit. Daraufhin findet eine Review der abgegebenen Preprints durch die weiteren Teilnehmer des Seminars statt. Jedem Studierenden werden hierfür 3-4 Paper anderer Studierender zugeteilt, welche von Ihnen reviewed werden. Die Review jedes Papers muss sich inhaltlich auf das gesamte Paper erstrecken und mindestens 400 Zeichen (für jedes Paper) enthalten. Studierende erhalten somit schon vor der endgültigen Abgabe der Seminararbeit Feedback von den anderen Teilnehmern des Seminars. Nach den Reviews finden die Vorträge statt. Abschließend werden die fertigen Seminararbeiten abgegeben.
Die Gesamtnote ergibt sich aus dem Preprint, den verfassten Reviews zu den Papern der anderen Studierenden, dem Vortrag und der finalen Seminararbeit.
Die Nichtabgabe des Abstracts, des Preprints, der Reviews oder der finalen Seminararbeit sowie ein Nichterscheinen zum Vortragstermin führt zum Nichtbestehen des Seminars.
Einzuhaltende Abgaben und Termine während des Semesters:
Vorbesprechung und Themenvergabe: 27.10.2021, 17.30 Uhr
Abgabe Abstracts: 19.11.2021
Abgabe Preprint: 07.01.2022
Abgabe Reviews: 20.01.2022
Vorträge: 24.01 und 25.01.2022
Finale Abgabe der Seminararbeiten: 07.02.2022
Weitere Informationen sowie Themenvorschläge finden Sie auf der Webseite des Lehrstuhls unter legalinf.de und im CMS.
Requirements: Es wird erwartet, dass Teilnehmer in der Lage sind, Vorträgen in deutscher Sprache zu folgen.
The rapid progress in artificial intelligence and machine learning has lead to the deployment of AI-based systems in a number of areas of modern life, such as manufacturing, transportation, and healthcare. However, serious concerns about the safety and trustworthiness of such systems still remain, due to the lack of assurance regarding their behavior. To address this problem, significant efforts in the area of formal methods in recent years have been dedicated to the development of rigorous techniques for the design of safe AI-based systems.
In this seminar, we will read and discuss research papers that present the latest results in this area. We will cover a range of topics, including the formal specification and verification of correctness properties of AI components of autonomous systems, and the design of reinforcement learning agents that respect safety constraints.
Each participant will give a presentation of an assigned paper, followed by a group discussion. All students are expected to read each paper carefully and to actively participate in the discussions. Each student will write a summary of the paper they have presented, including a general overview of the topic and reflecting the group discussion. Additionally, each student will be required to submit for 3 of the papers discussed in the seminar a short one-page review, describing the paper's strengths and weaknesses. Reviews are expected to be turned in at the beginning of the class during which the paper will be presented. In addition to the review, 2 questions to the presenter of the paper should be submitted.
Requirements: There are no formal prerequisites for this seminar. However, participants are expected to have strong interest in formal verification and/or machine learning, and knowledge in these areas would definitely be helpful.
Information flow security has been a hot topic in recent years, with side-channel attacks like Spectre showing how vulnerable much of our information infrastructure is. In this seminar, students will learn to present, discuss, and summarize papers that aim at formalizing, analyzing and automatically fixing information leaks. The seminar is split into two parts. The first part will take the form of reading sessions, where we lay the foundations of the topic. For the second part, each student is assigned a recent paper from the research area. Students will present their paper and will write a seminar paper on the topic assigned to them, taking into account connections to the topics discussed in the seminar.
Requirements: Basic knowledge of computer security and formal logic is assumed. More detailed knowledge about formal security properties and verification/automated reasoning is beneficial, but not necessary.
While the Internet has started as a research effort, it has consistently evolved throughout the decades into the largest commercial network. Today, many research efforts focus on understanding the Internet's structural trends, optimizing its packet delivery, and laying the foundations for future developments. In this seminar, you will receive a closer look at bleeding-edge research published at the top conferences in our domain. Discussing state-of-the-art approaches and recent findings from a broad range of network-related topics with your peers and instructors will provide you with a deep understanding of your assigned topic. Preparing the accompanying research survey and topic presentation will not only strengthen your academic writing but also help you to present your future work in a more accessible and structured way.
For further information please refer to our course page:
Requirements: Participants should have successfully participated in "Data Networks" or an equivalent course.
This seminar on hybrid AI is concerned with selected hybrid intelligent systems that combine techniques from machine learning with symbolic techniques from knowledge representation and reasoning. Both types of AI techniques have their strengths and limitations. While deep learning systems have been quite successfully applied to, for example, pattern recognition, image interpretation, speech recognition and translation, they can be characterized as overly data hungry, susceptible to adversarial attacks, opaque (non-interpretable by humans), and not informed by general principles such as causality or common-sense and domain knowledge. The successes of symbolic reasoning techniques (“good old fashioned AI”) are in such applications as automated action planning (human-understandable, traceable), diagnosis, design tasks, and question answering by cognitive virtual assistants but are often quite limited by the need of expensive, explicit knowledge acquisition and modelling, inefficient logic-based reasoning, and instability in the presence of noisy data. There is a consensus in the AI community that symbiotic, profound integration or combination of machine learning and reasoning is essential for human-level AI in general.
In this seminar, we will take a closer look at selected techniques and systems for hybrid learning and reasoning, and discuss their strengths and weaknesses. The seminar type is classic in the sense that registered participants will present assigned topics and discuss the strength and weaknesses of presented approaches. In addition, there will be two dedicated opponents for each presentation of an assigned topic.
Seminar website: http://www.dfki.de/~klusch/HyLEAR-seminar-ws21
Due to the ongoing COV19 pandemics, the seminar will be held virtually;
later transition to physical or hybrid meeting possible.
Requirements: This seminar aims primarily at master students in Computer Science who preferably hold a B.Sc. degree in this or related field. Good knowledge in AI (introductory course on AI covering symbolic knowledge representation and reasoning, machine learning, automated planning) is required.
Advances in technology have made our homes smarter. Nowadays, most appliances at home (e.g., lamps, heating systems, … ) feature a microcontroller and a touch interface. These interfaces extend interaction beyond a screen and leverage the benefits of physical interaction in the real world. This course focuses on state-of-the-art technologies for touch sensing alongside key questions regarding how we interact using touch on real-world objects and surfaces.
The seminar will cover the following topics:
Technologies for touch sensing
Prototyping and digital fabrication
Gesture detection and classification
Applications for robotics, wearable computing, Internet of Things
For further information please refer to our course page:
Requirements: This is a Master-level seminar, which can also be taken by Bachelor students from the 5th study semester and above.
Basic knowledge in hardware programming (e.g., some experience with Arduino) and with simple electronics is a must-have requirement for this hands-on course, e.g., as covered in the lecture on Interactive Systems.
In this seminar, students will learn to present, discuss, and summarize papers in different areas of Web security. The seminar is taught as a combination of a reading group with weekly meetings and a regular seminar, where you have to write a seminar paper. Specifically, each student will get a single topic assigned to them, consisting of two papers (a lead and follow-up paper).
For the weekly meetings, all students have to have read the lead paper and must state at least three questions before the meeting. In the meeting, the assigned student will present the follow-up paper (20 minute presentation + 10 minute Q/A). Afterward, the entire group will discuss both papers.
Moreover, each student will write a seminar paper on the topic assigned to them, for which the two papers on the topic serve as the starting point.
The seminar takes place on *Mondays, 10-12*. For a more detailed timeline, including the list of topics, please see https://cms.cispa.saarland/jaws21/. **Note that the seminar will be held in person and remote attendance is tricky to impossible**
Requirements: No specific requirements, but having taken the Foundations of Web Security lecture will definitely help.
Deep learning is the predominant machine learning paradigm in natural language processing (NLP). This approach not only gave huge performance improvements across a large variety of natural language processing tasks. It also allowed for a much easier integration of real world knowledge and visual information into NLP systems. However, a big problem of deep learning is the need for massive amounts of training data. Therefore in some of the topics you have to look into methods that can cope with this issue, e.g. by automatically creating noisy training data. Most likely the seminar this year will also have a strong emphasis on theory.
See also: https://www.lsv.uni-saarland.de/block-seminar-machine-learning-for-natural-language-processing-spring-2022/
Requirements: knowledge in ML
Image processing and computer vision have benefited from a number of key ideas that have fertilised the subsequent development enormously. The first goal of this seminar is to study a number of publications that have played a fundamental role in this context and that are cited very often. In addition, we will cover some of the most interesting publications from recent conferences. Additional information can be found at https://www.mia.uni-saarland.de/Teaching/maia21.shtml
Requirements: The seminar is for advanced bachelor or master students in Visual Computing, Mathematics, or Computer Science. Basic mathematical knowledge (e.g. Mathematik für Informatiker I-III) and some knowledge in image processing and computer vision is required. Some machine learning knowledge can be helpful for the later presentations but is not a requirement.
Planning is the sub-area of AI concerned with complex action-choice problems, which occur in a broad range of applications ranging from game playing to smart production. Learning is a natural approach to planning effectively in a given application, and recent results on complex board games (AlphaGo/Zero systems series) has shown the power of this approach. Yet beyond board games this approach is still in its infancy, and strong generalization across structure such as different goals and scaling instance size remains a widely open research problem. The seminar covers works at the current research frontier investgating neural rchitectures in general planning.
Requirements: AI planning side: AI core course minimally, AI Planning course preferred
Neural networks side: good basic knowledge, ideally at least one lecture relevant to this topic
Machine learning has witnessed tremendous progress during the past decade, and data is the key to such success. However, in many cases, machine learning models are trained on sensitive data, e.g., biomedical records, and such data can be leaked from trained machine learning models. In this seminar, we will cover the newest research papers in this direction.
Requirements: Students are required to have basic knowledge of data mining and machine learning.
Program analysis is a mature research area at the intersection of programming languages, formal methods, and software engineering. One of its main applications is automatic vulnerability detection. However, the complexity of modern systems is overwhelming and the vulnerabilities to be detected are increasingly sophisticated. To account for these particularities, many recent approaches advocate for lightweight program analysis techniques or for hybrid methods, i.e., static and dynamic analysis. This seminar explores the trade-offs involved in designing a program analysis that scales to analyzing the security of real systems.
We will discuss recent research papers in this area, in a reading group format. Each week, one student will present two papers covering a given topic, followed by a discussion. All participants are expected to actively participate in the discussion by asking questions.
You can find more details about the seminar and the list of topics to be discussed on the seminar's page: https://cms.cispa.saarland/pa4vd_2122/
Requirements: The students are expected to have good software engineering skills and a familiarity with the most important classes of vulnerabilities, e.g., buffer overflow, XSS.
Deep learning has achieved major breakthroughs in a variety of tasks. Yet, it comes at a considerable computational cost, which is exaggerated by the recent trend towards ever wider and deeper neural network architectures. Instead, many problems can be solved with the help of extremely sparse neural network architectures but finding and training them is a non-trivial task. According to the recent lottery ticket hypothesis, such sparse architectures can be identified by pruning large randomly initialized neural networks. In this seminar, we will present recent algorithmic advancements in this direction, gain theoretical insights into the existence of lottery tickets, identify open problems, and discuss common challenges in the quest for winning lottery tickets.
-Kick-off meeting in the first week of the semester (date and time tbd).
-We will have a block course in the spring break (date and time tbd at kick-off meeting) with one presentation and discussion of a topic per person.
-Note that some (light load of) written deliverables will be due before the block course meeting and a seminar paper one week after the meeting.
More information can be found here:
Requirements: The course has no formal requirements but preference will be given to Master Students in Computer Science and related fields with prior knowledge in deep learning.
Monte Carlo ray tracing is a popular technique to render realistic images. It is used for movies, architecture, video games, and product design. This seminar looks at a broad range of methods to make rendering via Monte Carlo ray tracing more efficient. We will look at rendering algorithms, from a basic path tracer to photon mapping, at sampling and material models, Markov chains and path guiding, and more. Each student will give a presentation on an assigned paper, write a short summary, and reproduce the key idea in a simplified setting.
Requirements: Basic understanding of computer graphics is assumed, for example through our Computer Graphics core lecture.
In the recent years, algorithms for convex optimization have revolutionized the design of algorithms, both for discrete as well as continuous optimization problems. At present, the fastest known algorithms for problems such as maximum flow in graphs, maximum matching in bipartite graphs, and submodular function minimization involve the use of algorithms for convex optimization like the gradient descent, mirror descent, interior point methods, and cutting plane methods. The goal of this course is to gain an understanding of the algorithms for convex optimization and see how they find applications in solving combinatorial optimization problems.
In this seminar course, we read the book Algorithms for Convex Optimization by Nisheeth Vishnoi. This is the most contemporary book in the area. The instructors will present the introductory chapters of the book (Chapter 2,3,4) in the first few weeks of the course. Every lecture of the subsequent week will consist of 2-3 student presentations. Each week (after the introductory chapters are covered), all the students are expected to prepare roughly one chapter of the book. The contents of the chapter would be divided into 2-3 logical parts, each forming one individual presentation. The decision on who presents in the coming lecture will be based on a random choice that will be made just before the lecture begins. Thus, every student is expected to be prepared with one chapter of the book every week. A student can refuse to make the presentation, after the random decision is made, at most twice throughout the course. An absence from the lecture counts as one refusal. Note that if the course is conducted non-virtually then the presentations could be made on the blackboard/whiteboard. At the end of the course, a student may or may not submit a written summary of one of the important chapters in the book. Submitting a summary is optional and can lead to an increase or decrease in the grade depending on its quality.
If you have any doubts while preparing for your presentations, you can reach out to one of the instructors well in advance before the day of presentation. Please make sure that you read the section on prerequisites above before you register.
See also https://www.mpi-inf.mpg.de/departments/algorithms-complexity/teaching/winter21/reading-group
Requirements: You should have an aptitude for mathematical thinking. A solid background in algorithms and data structures is a plus. This is an advanced seminar as it follows the most contemporary book on the topic. You will be expected to be prepared with one new chapter of the book every week. The target audience of this reading group are master students, PhD students, as well as postdocs.
Open-Source Software (OSS) projects have gained more and more popularity over the past decades.
As a result, the communities working on OSS projects have grown from small groups of volunteers to large, globally distributed teams.
This can lead to problems as (other than in companies) there often is no central management and the people working on the projects mostly govern and organize themselves with the help of Codes of Conduct and other measures.
To better understand and help improve collaboration in OSS projects, software engineering research has shown a great interest in the community structures and processes of OSS projects by using software analytics of the repository and communication channel histories of these projects.
In this seminar, we explore some of the topics about the human factor of OSS projects, such as the diversity of communities, social interactions of people, technical interactions, and how collaborators communicate among each other.
In this course, each participant has to perform an extensive literature search for the given topic.
Subsequently, the topic and the results of the literature research are incorporated into a presentation and a written thesis.
To aid the literature research and the presentations, this course includes two preparatory sessions at the beginning of the semester.
The student presentations will be held on-site at the university (under the caveat that the pandemic situation admits in-person sessions) in January and February 2022 Thursdays 12:15 PM - 2:00 PM.
The topic assignment will take place on Thursday October 28, at 12:15 PM. Further information will be provided via e-mail after the registration.
Requirements: Basic knowledge of software engineering
A digital twin is a digital representation of a tangible or intangible object from the real world in the digital world. In particular, they play a central role in the digitalization of industry as part of Industrie 4.0.
In this practical seminar you will learn about relevant concepts of Industrie 4.0 and implement a Robotic Digital Twin in small teams consisting of 2 - 4 students. We will provide a list of possible ideas, but you can also propose your own ideas. You will be able to work with different robotic systems, like self-driving robots, robot arms and quadcopters (drones).
This seminar is in cooperation with ZeMA (Zentrum für Mechatronik und Automatisierung) and will partially take place in the Power4Production Hall at ZeMA ( Eschberger Weg 46, 66121 Saarbrücken)
Requirements: To participate you should have
- basic knowledge in AI (computer vision, planning)
- good programming skills in Java,
- programming skills in Python or C++ if you want to focus on computer vision tasks
- beneficial: experience in Unity 3D
Optimization lies at the heart of many machine learning algorithms. This seminar teaches an overview of modern mathematical optimization methods, for applications in machine learning and data science. In particular, we will discuss the theoretical basics of stochastic optimization, scalability of algorithms to large datasets, and challenges in distributed optimization, such as for instance in decentralized or federated machine learning. We will cover a set of foundational papers, but also a selection of recent publications.
- This seminar will be organized in the block format, that is, all presentations will take place in the spring break 2022.
- A kick of meeting will be held virtually on October 25, 2021.
Note that - besides the block format - there are some written deliverables due during the semester, as well as a (mandatory) meeting with the tutor to get feedback on your report and presentation slides.
Additional information can be found at https://cms.cispa.saarland/optml_seminar_21/.
Requirements: This seminar aims primarily at master students in Computer Science or related fields. Previous experience in machine learning, data analysis, or optimization is beneficial.
Graph Neural Networks (GNNs) have emerged as a fundamental building block in many artificial intelligence systems. Even beyond uses where the graph structure is explicit (e.g. social networks), they show impressive performance for general object-oriented perception, representation, and reasoning. In this seminar we will cover GNNs that are not only accurate or efficient, but also robust, privacy-preserving, fair, uncertainty-aware, and explainable. We will explore how GNNs fail w.r.t. these trustworthiness aspects and how to improve them.
Organization (block format):
Each student will receive a few research papers on a single topic which they should carefully read and analyze. Starting from these initial papers they should explore the surrounding literature and summarize their main ideas and findings in a 4-page seminar paper. Students will also participate in a peer-review process where they have to provide constructive feedback on each other's work (1 page review for 3 other papers). Finally, each student will prepare and deliver a presentation about their topic during a block seminar at the end of the semester.
- Seminar paper (40%)
- Presentation (30%)
- Reviews (30%, 10% for each review)
Schedule (exact dates and times tbd):
- Kick-off meeting at the start of the semester (online via Zoom)
- Deadline for the first draft of the seminar paper
- Deadline for the final version of the seminar paper
- Deadline for the reviews
- Feedback round / practice talk with your supervisor
- Final presentations at the end of the semester
News and additional information can be found on the seminar website: https://cms.cispa.saarland/tgnn_ws21/
Requirements: No formal requirements. Please provide a concise overview (short bullet list) of your previous experience with machine learning in the text box below. Preference will be given to master students in computer science and related fields with prior knowledge about machine learning and graph neural networks.
This seminar is done in cooperation with the Centigrade GmbH.
Your task will be to come up with a gamified solution to motivate specific user groups (based on their player type) to use a treadmill during office work. To this end, you will conduct several design steps before starting the implementation. As you usually have limited resources in practice (e.g., limited time, limited access to testing opportunities, limited access to participants), you will learn and use techniques that are also used in an industry context today. We will also have a mobile test setup in which the game (with a treadmill) can be tested.
For more information (including requirements to pass and all dates) please check: https://umtl.cs.uni-saarland.de/teaching/winter-2021/2022/seminar-walk-while-work-ux-driven-development-of-player-type-centric-motion-games.html
Important: Please check the LSF system whether this seminar is applicable for your course of studies!
Requirements: You need to have passed the core lecture "Human Computer Interaction" (HCI) to attend this seminar. If you do not have passed this lecture or it does not count for your course of studies, please do not pick this seminar.