Search Results for author: Julian Busch

Found 5 papers, 3 papers with code

DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classification

1 code implementation31 Jul 2023 Sandra Gilhuber, Julian Busch, Daniel Rotthues, Christian M. M. Frey, Thomas Seidl

Node classification is one of the core tasks on attributed graphs, but successful graph learning solutions require sufficiently labeled data.

Active Learning Graph Learning +1

NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification

no code implementations5 Mar 2021 Julian Busch, Anton Kocheturov, Volker Tresp, Thomas Seidl

Malicious software (malware) poses an increasing threat to the security of communication systems as the number of interconnected mobile devices increases exponentially.

General Classification Malware Detection

Learning Self-Expression Metrics for Scalable and Inductive Subspace Clustering

1 code implementation27 Sep 2020 Julian Busch, Evgeniy Faerman, Matthias Schubert, Thomas Seidl

Consequently, our model benefits from a constant number of parameters and a constant-size memory footprint, allowing it to scale to considerably larger datasets.

Clustering Metric Learning

PushNet: Efficient and Adaptive Neural Message Passing

1 code implementation4 Mar 2020 Julian Busch, Jiaxing Pi, Thomas Seidl

We find that our models outperform competitors on all datasets in terms of accuracy with statistical significance.

Inductive Bias Node Classification +1

Semi-Supervised Learning on Graphs Based on Local Label Distributions

no code implementations15 Feb 2018 Evgeniy Faerman, Felix Borutta, Julian Busch, Matthias Schubert

Precisely, we propose a new node embedding which is based on the class labels in the local neighborhood of a node.

Attribute General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.