no code implementations • 6 Oct 2023 • Franka Bause, Samir Moustafa, Johannes Langguth, Wilfried N. Gansterer, Nils M. Kriege
Message passing neural networks iteratively generate node embeddings by aggregating information from neighboring nodes.
1 code implementation • 19 Sep 2022 • Franka Bause, Nils M. Kriege
The classical Weisfeiler-Leman algorithm aka color refinement is fundamental for graph learning with kernels and neural networks.
1 code implementation • 12 Sep 2022 • Lutz Oettershagen, Nils M. Kriege, Claude Jordan, Petra Mutzel
We introduce the \emph{temporal graphlet kernel} for classifying dissemination processes in labeled temporal graphs.
1 code implementation • 22 May 2022 • Nils M. Kriege
Random walk kernels have been introduced in seminal work on graph learning and were later largely superseded by kernels based on the Weisfeiler-Leman test for graph isomorphism.
1 code implementation • 8 Feb 2022 • Lutz Oettershagen, Petra Mutzel, Nils M. Kriege
We propose the Temporal Walk Centrality, which quantifies the importance of a node by measuring its ability to obtain and distribute information in a temporal network.
no code implementations • 18 Dec 2021 • Christopher Morris, Yaron Lipman, Haggai Maron, Bastian Rieck, Nils M. Kriege, Martin Grohe, Matthias Fey, Karsten Borgwardt
In recent years, algorithms and neural architectures based on the Weisfeiler--Leman algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a powerful tool for machine learning with graphs and relational data.
no code implementations • 12 May 2021 • Christopher Morris, Matthias Fey, Nils M. Kriege
In recent years, algorithms and neural architectures based on the Weisfeiler-Leman algorithm, a well-known heuristic for the graph isomorphism problem, emerged as a powerful tool for (supervised) machine learning with graphs and relational data.
2 code implementations • 16 Jul 2020 • Christopher Morris, Nils M. Kriege, Franka Bause, Kristian Kersting, Petra Mutzel, Marion Neumann
We provide Python-based data loaders, kernel and graph neural network baseline implementations, and evaluation tools.
2 code implementations • ICLR 2020 • Matthias Fey, Jan E. Lenssen, Christopher Morris, Jonathan Masci, Nils M. Kriege
This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs.
Ranked #12 on Entity Alignment on DBP15k zh-en (using extra training data)
no code implementations • 14 Oct 2019 • Lutz Oettershagen, Nils M. Kriege, Christopher Morris, Petra Mutzel
Hence, we confirm that taking temporal information into account is crucial for the successful classification of dissemination processes.
no code implementations • 19 Aug 2019 • Nils M. Kriege
Assignment kernels are based on an optimal bijection between the parts and have proven to be an effective alternative to the established convolution kernels.
no code implementations • 28 Mar 2019 • Nils M. Kriege, Fredrik D. Johansson, Christopher Morris
Graph kernels have become an established and widely-used technique for solving classification tasks on graphs.
no code implementations • 29 Jan 2019 • Nils M. Kriege, Pierre-Louis Giscard, Franka Bause, Richard C. Wilson
In this paper, we develop an algorithm which can find an optimal assignment in linear time when the cost function between objects is represented by a tree distance.
no code implementations • 16 Feb 2018 • Nils M. Kriege, Matthias Fey, Denis Fisseler, Petra Mutzel, Frank Weichert
To this end, the distance measure is used to implement a nearest neighbor classifier leading to a high computational cost for the prediction phase with increasing training set size.
no code implementations • 2 Mar 2017 • Nils M. Kriege, Marion Neumann, Christopher Morris, Kristian Kersting, Petra Mutzel
On this basis we propose exact and approximative feature maps for widely used graph kernels based on the kernel trick.
no code implementations • 1 Oct 2016 • Christopher Morris, Nils M. Kriege, Kristian Kersting, Petra Mutzel
While state-of-the-art kernels for graphs with discrete labels scale well to graphs with thousands of nodes, the few existing kernels for graphs with continuous attributes, unfortunately, do not scale well.
no code implementations • NeurIPS 2016 • Nils M. Kriege, Pierre-Louis Giscard, Richard C. Wilson
The success of kernel methods has initiated the design of novel positive semidefinite functions, in particular for structured data.
Ranked #2 on Graph Classification on NCI109