Message-Passing on Directed Acyclic Graphs Prevents Over-Smoothing

Despite the rising popularity of message-passing neural networks (MPNNs), their ability to fit complex functions over graphs is limited as node representations become more similar with increasing depth—a phenomenon known as over-smoothing. Most approaches to mitigate...

OoDIS: Anomaly Instance Segmentation Benchmark

Safe navigation of self-driving cars and robots requires a precise understanding of their environment. Training data for perception systems cannot cover the wide variety of objects that may appear during deployment. Thus, reliable identification of unknown objects,...

WestAI im Heise-KI-Podcast

Im Heise-KI-Podcast spricht Dr. Stefan Kesselheim vom Jülich Supercomputing Centre über OpenGPT-X und JUPITER, den ersten Exascale Supercomputer Europas. Das KI-Servicezentrum WestAI rückt im Gespräch ebenfalls in den Mittelpunkt. Dr. Kesselheim, der als »Lead...