While message-passing neural networks (MPNNs) are the most popular architectures for graph learning, their expressive power is inherently limited. In order to gain increased expressive power while retaining efficiency, several recent works apply MPNNs to subgraphs of the original graph.
The Fraunhofer-Gesellschaft (www.fraunhofer.com) currently operates 76 institutes and research institutions throughout Germany and is the world’s leading applied research organization. Around 30 000 employees work with an annual research budget of 2.9 billion euros.
The IEEE Signal Processing Society (SPS) is happy to announce that Prof. Yonggang Wen will be the new Editor-in-Chief (EIC) of the IEEE Transactions on Multimedia (T-MM). His three-year term will be from January 2023 to December 2025.
Over the past twenty years, functional connectivity of the human brain has been studied using tools from complex network theory. One such tool is community detection which is fundamental for uncovering the links between structure and function in complex networks.