Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
How does compression of Large Language Models affect their bias?
Published:
14th June 2024
How can we measure the bias of Large Language Models?
Published:
14th May 2024
How can we make Large Language Models smaller?
Published:
4th May 2024
Do Large Language Models have to be so big?
Published:
13th April 2024
portfolio
Portfolio item number 1
Published:
Short description of portfolio item number 1
Portfolio item number 2
Published:
Short description of portfolio item number 2
publications
What Do Temporal Graph Learning Models Learn?
Published in , 2025
Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models. However, recent work has raised concerns about the reliability of benchmark results, noting issues with commonly used evaluation protocols and the surprising competitiveness of simple heuristics. This contrast raises the question of which properties of the underlying graphs temporal graph learning models actually use to form their predictions. We address this by systematically evaluating seven models on their ability to capture eight fundamental attributes related to the link structure of temporal graphs. These include structural characteristics such as density, temporal patterns such as recency, and edge formation mechanisms such as homophily. Using both synthetic and real-world datasets, we analyze how well models learn these attributes. Our findings reveal a mixed picture: models capture some attributes well but fail to reproduce others. With this, we expose important limitations. Overall, we believe that our results provide practical insights for the application of temporal graph learning models, and motivate more interpretability-driven evaluations in temporal graph learning research.
Recommended citation: Hayes et al. (2025). "What Do Temporal Graph Learning Models Learn?" arxiv.org.
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Network Science
Masters course exercise, University of Mannheim, Chair of Data Science in the Economic and Social Sciences, 2025
Responsible for exercises for a Masters level course on Network Science. Explained and discussed solutions to problem sheets with students. Additionally, assessment of assignment submissions.
What to LLMs know about social networks?
Team project supervision, University of Mannheim, Chair of Data Science in the Economic and Social Sciences, 2025
Generated an initial project concept for a group of students. Supervised and advised the students to complete a successful research project.
Large Language Models for the Economic and Social Sciences
Masters course exercise, University of Mannheim, Chair of Data Science in the Economic and Social Sciences, 2025
Created exercises for a Masters level course on applying LLMs to research. Students gain hands-on experience with the rigourous application of these models to tasks including sentiment analysis and gain first-hand experience of some of the potential risks or pitfalls of these applications.
Data Science Seminar
Masters-level seminar, University of Mannheim, Chair of Data Science in the Economic and Social Sciences, 2025
Identified cutting edge research papers on fairness in GNNs for students to develop the skill of working with scientific publications. Supervised students in presenting the research papers and completing a comparison of a range of different approaches to the same problem.