N
Nils M. Kriege
Researcher at Technical University of Dortmund
Publications - 76
Citations - 1634
Nils M. Kriege is an academic researcher from Technical University of Dortmund. The author has contributed to research in topics: Computer science & Time complexity. The author has an hindex of 15, co-authored 68 publications receiving 1072 citations. Previous affiliations of Nils M. Kriege include University of Vienna & University of Bonn.
Papers
More filters
Posted Content
TUDataset: A collection of benchmark datasets for learning with graphs.
Christopher Morris,Nils M. Kriege,Franka Bause,Kristian Kersting,Petra Mutzel,Marion Neumann +5 more
TL;DR: The TUDataset for graph classification and regression is introduced, which consists of over 120 datasets of varying sizes from a wide range of applications and provides Python-based data loaders, kernel and graph neural network baseline implementations, and evaluation tools.
Journal ArticleDOI
A Survey on Graph Kernels
TL;DR: Graph kernels have become an established and widely used technique for solving classification tasks on graphs as mentioned in this paper, and a comprehensive overview of techniques for kernel-based graph classification developed in the past 15 years is given in this survey.
Proceedings Article
Subgraph Matching Kernels for Attributed Graphs
Nils M. Kriege,Petra Mutzel +1 more
TL;DR: In this paper, the authors proposed graph kernels based on subgraph matchings, i.e. structure-preserving bijections between subgraphs, for attributed graphs.
Journal ArticleDOI
A survey on graph kernels
TL;DR: This survey gives a comprehensive overview of techniques for kernel-based graph classification developed in the past 15 years and describes and categorizes graph kernels based on properties inherent to their design, such as the nature of their extracted graph features, their method of computation and their applicability to problems in practice.
Proceedings Article
Deep Graph Matching Consensus
TL;DR: This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs that scales well to large, real-world inputs while still being able to recover global correspondences consistently.