Invert color theme

Welcome to the MALEO Group

The Machine Learning and Optimisation (MALEO) group, led by Prof. Dr. Heike Trautmann, was established in October 2023 at Paderborn University, Germany.

Our theoretical and empirical research mainly focuses on (Trustworthy) Artificial Intelligence, Data Science, (Automated) Machine Learning, Automated Algorithm Selection and Configuration, Exploratory Landscape Analysis, Analysis of Randomised Search Heuristics, and (Multiobjective) Evolutionary Optimisation. In interdisciplinary collaboration, we are moreover addressing Computational Social Science topics such as Social Influence Analysis and Disinformation Campaign Detection in Open Online Media. We have diverse and extensive national and international collaborations with particularly strong links to the University of Twente, Enschede. At the European level, we strongly support the Confederation of Laboratories for Artificial Intelligence Research in Europe (CLAIRE) and the European Research Center for Information Systems (ERCIS).

For a more fine-grained description visit our research page. For teaching related topics see our official UPB website.

Latest Blog Post

Moritz Seiler officially joined MALEO

Posted by Jakob Bossek on 2 April 2024

Today is the first official working day of our new staff member Moritz Vinzent Seiler! Moritz has been a good colleague for many years and we are delighted that he decided to continue his academic career at Paderborn University.

Read more

Group Name and Logo

Photo of a maleo.
Source: WikiPedia (licenced under CC BY-SA 4.0 DEED).

We are the Machine Learning and Optimisation Group, short MALEO. Coincidentally, this is also the name of an exotic bird 🐦 (lat. Macrocephalon maleo); see, e.g., the maleo WikiPedia page.

The linked dots in our logo have different meanings representing the various research foci and backgrounds of our staff members.

  • Graph problems: we are interested in optimisation problems on graphs like the Traveling Salesperson Problem (TSP) and also in social media analysis. Social networks and permutation problems can be naturally represented by graphs (objects with relations).

  • Multi-objective optimisation: the dots represent a set of non-dominated points / set of compromise solutions of a bi-objective problem if the first objective is to be minimised and the second objective is to be maximised.

  • Statistics: the linked dots can be interpreted as an empirical distribution function of data that is normally distributed.