Efficient Graph Kernels by Randomization

By Marion Neumann, Novi Patricia, Roman Garnett, Kristian Kersting. 2012

66 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Pre-training Graph Neural Networks with Kernels (2018, neutral): “, 2010], the propagation kernel (PK) [Neumann et al., 2012], and the Weisfeiler-Lehman subtree kernel (WL) [Shervashidze et al.”
An End-to-End Deep Learning Architecture for Graph Classification (2018, methodology): “2010), the propagation kernel (PK) (Neumann et al. 2012), and the Weisfeiler-Lehman subtree kernel (WL) (Shervashidze et al.”
Tree-Based Kernel for Graphs With Continuous Attributes (2015, background): “adopt slower kernels o r discretizing/ignoring the continuous attributes of the gr aphs, the latter approach was usually the preferred one [8].”
An Aligned Subtree Kernel for Weighted Graphs (2015, background): “In general, note that any graph kernel what can deal with continuous node attributes (Neumann et al., 2012; Feragen et al., 2013) can be adapted to work on edge weighted graphs by replacing the original graph with its corresponding line graph, effectively moving the weights from the edges to the nod”
Ordered Decompositional DAG kernels enhancements (2015, methodology): “Moreover, we adopted from [42] two real-world image datasets: MSRC9-class and MSRC21-class(3).”
Graph Capsule Convolutional Neural Networks (2018, background): “Another part of this work goes into efficiently computing these kernels either through exploiting some structure dependency, or approximation, or randomization (Feragen et al., 2013; de Vries, 2013; Neumann et al., 2012).”
Graph Invariant Kernels (2015, methodology): “The symbol T denotes the number of iterations and TV and w are parameters (see [Neumann et al., 2012]).”
InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization (2019, background): “Another line of research in this area focuses on efficiently computing these kernels either through exploiting certain structural dependencies, or via approximations/randomization [11, 9, 37].”
On Filter Size in Graph Convolutional Networks (2018, methodology): “Propagation kernels (PK) [30] follow a different idea, inspired by the diffusion process in graph node kernels (i.”