Graph convolutions have gained popularity due to their ability to efficiently operate on data with an irregular geometric structure. However, graph convolutions cause over-smoothing, which refers to representations becoming more similar with increased depth. However,...
The ability of message-passing neural networks (MPNNs) to fit complex functions over graphs is limited as most graph convolutions amplify the same signal across all feature channels, a phenomenon known as rank collapse, and over-smoothing as a special case. Most...
Aktuelle Herausforderungen in der Produktion, etwa der Fachkräftemangel, erhöhen die Notwendigkeit, Prozesse zu automatisieren und die Produktivität zu erhöhen. Multimodale Foundation-Modelle bieten diese Möglichkeit für eine Vielzahl an Anwendungen, indem sie aus...
The significant increase in data volume in recent years has prompted the adoption of knowledge graphs as valuable data structures for integrating diverse data and metadata. However, this surge in data availability has brought to light challenges related to...
Dataspaces have recently gained adoption across various sectors, including traditionally less digitized domains such as culture. Leveraging Semantic Web technologies helps to make dataspaces FAIR, but their complexity poses a significant challenge to the adoption of...
Dataspaces are regarded as a standardized solution for sharing data in a trusted way. However, providing and sharing high-quality data across dataspaces poses several scientific and technical challenges, opening new research avenues. Developing governance models and...
