The GAIN group investigates the application of Deep Learning techniques on
graphs to address various challenges in the field of Graph Learning.
The focus is on the study of dynamic graphs due to their high degree of
freedom in modeling tasks.
The research includes different topics such as:
- the development of Deep Learning models applicable for dynamic graphs
respecting the variety of existing graph types
and the associated difficulties,
- the consideration of different dynamics w.r.t. the graph structure
and attributes and consequent adaptations of established approaches,
- the installation of an appropriate explainability mechanism for the
developed models to achieve an applicability to real-world problems,
- the development of GNNs which enhance the efficiency and safety of power networks by directly making use of their topology
In cooperation withFraunhofer IEE,
problems from supply networks (electric power transmission)
serve as future applications of the algorithms arising from the GAIN project.