We are working in one of the youngest and fastest growing research areas of Machine Learning, which is aiming to continue the success of Deep Learning to data represented by graphs.
Currently, our focus is on the dynamics and explainability of Graph Neural Networks (GNNs).
By dynamic, we mean to develop GNN-algorithms that can deal with changes in the topology of a graph or changing graph attributes. In the simplest case that might be new appearing nodes or a change in an attribute describing a node.
At the same time, we want our algorithms to be explainable, which means that either inherently or post-hoc our algorithms should give a reason for their predictions.
We chose this focus, because dynamics will enable the use of GNN-based methods in supply structure networks and therefore help with renewable energies, while explainability will make their application more likely.
We are situated at the department ofIntelligent Embedded Systemsat the university of Kassel and project partners with theFraunhofer Institute for Energy Economics and Energy Systems Technology (Fraunhofer IEE)in Kassel.
Enjoy browsing our pages and feel free to contact us via the addresses provided in thecontactsection. You can also find our PGP-keys there. Have fun!