76 citations · 95 across the 6 of their papers we have counts for
6 papers
Geometry-aware PINNs for Turbulent Flow Prediction
Shinjan Ghosh, Julian Busch, Georgia Olympia Brikis +1
Design exploration or optimization using computational fluid dynamics (CFD) is commonly used in the industry. Geometric variation is a key component of such design problems, especi…
DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classification
Sandra Gilhuber, Julian Busch, Daniel Rotthues +2
Node classification is one of the core tasks on attributed graphs, but successful graph learning solutions require sufficiently labeled data. To keep annotation costs low, active g…
NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification
Julian Busch, Anton Kocheturov, Volker Tresp +1
Malicious software (malware) poses an increasing threat to the security of communication systems as the number of interconnected mobile devices increases exponentially. While some…
Learning Self-Expression Metrics for Scalable and Inductive Subspace Clustering
Julian Busch, Evgeniy Faerman, Matthias Schubert +1
Subspace clustering has established itself as a state-of-the-art approach to clustering high-dimensional data. In particular, methods relying on the self-expressiveness property ha…
PushNet: Efficient and Adaptive Neural Message Passing
Julian Busch, Jiaxing Pi, Thomas Seidl
Message passing neural networks have recently evolved into a state-of-the-art approach to representation learning on graphs. Existing methods perform synchronous message passing al…
Semi-Supervised Learning on Graphs Based on Local Label Distributions
Evgeniy Faerman, Felix Borutta, Julian Busch +1
Most approaches that tackle the problem of node classification consider nodes to be similar, if they have shared neighbors or are close to each other in the graph. Recent methods f…