This seminar simulates a machine learning conference, where the students take on the role of authors and reviewers. It consists of multiple phases.
Attend the mandatory first meeting either in person or remotely (details on TUWEL).
You select two topics/papers (i.e., two bullet points) from one of the topics below. You will work with the material mentioned in the overview and the topic-specific resources.
You choose your own topic to work on. This can be some existing machine learning paper/work or an own creative idea in the context of machine learning. We strongly encourage you to start from existing papers from the following venues: NeurIPS, ICML, ICLR, COLT, AISTATS, UAI, JMLR, MLJ. Importantly, your idea has to be specific and worked out well. Nevertheless, choose one of our suggestions as well.
Independent of the option you chose, understand the fundamentals of your topic and try to answer the following questions:
Select topics and write a short description of them together with the answers to the questions (~3 sentences should be sufficient) in TUWEL.
We can only accept your own proposals if you can answer the mentioned questions and have a well worked out topic.
You and your fellow students will act as reviewers and bid on the topics of your peers you want to review. Based on the biddings, we (in the role as chairs of the conference) will select one of each student’s proposals as the actual project you will work on for the rest of this semester. You do not need to work on the other project, anymore. Additionally, we will also assign two different projects from other students to you, which you will have to review later in the semester.
Now the actual work starts. Gather deep understanding of your topic, write a first draft of your report and give a 5-minute presentation. Feel free to go beyond the given material.
You will schedule two meetings with your supervisor to discuss your progress, but do not hesitate to contact him/her if you have any questions.
You will again act as a reviewer for the conference by writing two reviews, one for each draft report assigned to you.
Based on the reviews from your peers (and our feedback) you will further work on your topic.
Give a final presentation and submit your report.
You should have access to the literature and papers through Google scholar, DBLP, the provided links, or the TU library.
Motivation: Ability to learn logically definable concepts from labelled data is a theoretical model of Machine Learning which is explainable by design, and integrates ideas from both logic (especially finite model theory) and PAC Learning.
Overview:
Papers and topics:
Motivation: We aim to understand computation in the brain. Our research either uses recent Deep learning technology to analyze brain recordings (AI for neuroscience), or we derived comptutation principles from the neuron to inspire future generation of AI algorithms (brain inspired computing).
Expected outcomes:
Papers:
Motivation:
Data science algorithms are successfully utilized in many different areas on a daily basis. Typically, these algorithms solve problems that are NP-hard and often even hard to approximate. Understanding why these algorithms work so well in practice is an important question in the area of beyond worst-case analysis.
Overview:
The book “Beyond the Worst-Case Analysis of Algorithms” by Tim Roughgarden provides a good starting point for literature search. We are particularly interested in the results related to Chapters 6, 7, 20, 28 and 30 of this book. It is encouraged to also look at other chapters of this book and papers related to these chapters.
Supervisor: Prof. Dr. Stefan Neumann
While our primary focus is on healthcare, RL has widespread applications in diverse domains such as finance, robotics, gaming, and autonomous systems. The adaptability of RL algorithms makes them suitable for addressing complex decision-making challenges in different fields.
PAC provides a mathematical foundation for ensuring that learned policies are close to optimal, instilling confidence in the reliability of RL algorithms. With PAC, RL agents can make decisions in critical healthcare scenarios with a high degree of certainty, mitigating risks associated with uncertain outcomes.
Motivation: Computing a disentangled representation is a very desirable property for modern deep learning architectures. Having access to individual, disentangled factors is expected to provide significant improvements for generalisation, interpretability and explainability.
Overview:
Papers and topics:
Motivation: Many datastructures have an innate structure that our neural networks should respect. For example the output of a graph neural networks should not change if we permute the vertices (permutation equivariance/invariance).
Overview:
Papers and topics:
Motivation: Machine learning has become a cornerstone of automated synthesis planning in organic chemistry. A key step in this process is reaction prediction. Over the past 15 years, numerous models and architectures (template-based, GNNs, transformers, …) have been developed to address this complex task. Yet, reaction prediction can refer to a range of distinct modeling tasks—such as predicting products, assessing feasibility, or classifying mechanisms. Comparing existing models is often non-trivial, as their assumptions and objectives vary and the boundaries between prediction tasks are often unclear. For instance, a model trained for product prediction may also be applied to assess reaction feasibility. This motivates the exploration of a formal framework that clarifies the relationships between different modeling approaches.
Papers:
Motivation: The ability of a model to adapt and perform well on new data is crucial. A model which generalises not only performs well on the training set, but on unseen data as well. Understanding and characterising why and how deep learning can generalise well is still an open question.
Overview:
Papers and topics:
Motivation: Graphs are a very general structure and can be applied to many areas: molecules and developing medicine, geographical maps, spread of diseases. They can be used to model physical systems and solve partial differential equations. Even images and text can be seen as a special case of graphs. Thus it makes sense to develop neural networks that can work with graphs. GNNs have strong connections to many classical computer science topics (algorithmics, logic, …) while also making use of neural networks. This means that work on GNNs can be very theoretical, applied or anything in between.
Overview:
Papers:
Note: For very long papers we do not expect you to read the entire appendix.
Motivation: Large language models such as ChatGPT are seeing a huge research interest. Some companies are releasing more or less free models, and open-source initiatives have sprung up.
Overview: In this seminar paper, an overview of the latest large language models that are available in various forms is given. This includes, in particular, an investigation of their performance, and an explanation how performance can be evaluated objectively at all.
Advisor: Prof. Clemens Heitzinger
Motivation:
Online social networks have become ubiquitous parts of modern societies, but recently they have been blamed for causing disagreement and polarization. Developing a theoretical understanding of these phenomena is still an active research question.
Papers:
Supervisor: Prof. Dr. Stefan Neumann
Motivation: Exploration of new perspectives opened by ML methods for complex quantum systems and/or improving machine learning methods from the point of view as a physical system of interacting elements
Overview: Statistical field theory for neural networks (Lecture notes) by Moritz Helias and David Dahmen, https://arxiv.org/abs/1901.10416
Related Works:
Advisor: Prof. Sabine Andergassen
Policy evaluation is a critical process that assesses the effectiveness of decision-making policies in healthcare. In dynamic healthcare environments, RL algorithms continuously assess and adjust policies based on real-time patient data, ensuring adaptability to evolving medical scenarios.
Motivation: Regulatory AI explores how technical systems can support accountability, transparency, and compliance in machine learning. The goal is to design models and data pipelines that can be audited, constrained, or certified: turning legal and ethical requirements into computable properties. This connects ML research on robustness, interpretability, and verification with questions of governance and oversight.
Overview:
Papers and topics:
In healthcare, making decisions is challenging due to complex and high-stakes scenarios. RL, as a dynamic decision-making framework, is uniquely positioned to handle the intricacies of healthcare scenarios by not only predicting outcomes but also adapting treatment strategies to evolving patient conditions.
Motivation: Transformers have revolutionized natural-language processing, and research has exploded since 2017.
Overview: In this seminar paper, the functioning of transformers is explained and an overview of the latest developments, regarding large language models, time-series predction, etc., is given.
Advisor: Prof. Clemens Heitzinger