A survey on graph kernels

NM Kriege, FD Johansson, C Morris - Applied Network Science, 2020‏ - Springer
Graph kernels have become an established and widely-used technique for solving
classification tasks on graphs. This survey gives a comprehensive overview of techniques …

A comprehensive survey of graph embedding: Problems, techniques, and applications

H Cai, VW Zheng, KCC Chang - IEEE transactions on …, 2018‏ - ieeexplore.ieee.org
Graph is an important data representation which appears in a wide diversity of real-world
scenarios. Effective graph analytics provides users a deeper understanding of what is …

Graph neural networks: foundation, frontiers and applications

L Wu, P Cui, J Pei, L Zhao, X Guo - … of the 28th ACM SIGKDD conference …, 2022‏ - dl.acm.org
The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

Weisfeiler and leman go neural: Higher-order graph neural networks

C Morris, M Ritzert, M Fey, WL Hamilton… - Proceedings of the …, 2019‏ - ojs.aaai.org
In recent years, graph neural networks (GNNs) have emerged as a powerful neural
architecture to learn vector representations of nodes and graphs in a supervised, end-to-end …

Weisfeiler and leman go machine learning: The story so far

C Morris, Y Lipman, H Maron, B Rieck… - Journal of Machine …, 2023‏ - jmlr.org
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 …

Weisfeiler and leman go sparse: Towards scalable higher-order graph embeddings

C Morris, G Rattan, P Mutzel - Advances in Neural …, 2020‏ - proceedings.neurips.cc
Graph kernels based on the $1 $-dimensional Weisfeiler-Leman algorithm and
corresponding neural architectures recently emerged as powerful tools for (supervised) …

Matching node embeddings for graph similarity

G Nikolentzos, P Meladianos… - Proceedings of the AAAI …, 2017‏ - ojs.aaai.org
Graph kernels have emerged as a powerful tool for graph comparison. Most existing graph
kernels focus on local properties of graphs and ignore global structure. In this paper, we …

On valid optimal assignment kernels and applications to graph classification

NM Kriege, PL Giscard… - Advances in neural …, 2016‏ - proceedings.neurips.cc
The success of kernel methods has initiated the design of novel positive semidefinite
functions, in particular for structured data. A leading design paradigm for this is the …

The multiscale laplacian graph kernel

R Kondor, H Pan - Advances in neural information …, 2016‏ - proceedings.neurips.cc
Many real world graphs, such as the graphs of molecules, exhibit structure at multiple
different scales, but most existing kernels between graphs are either purely local or purely …

Speqnets: Sparsity-aware permutation-equivariant graph networks

C Morris, G Rattan, S Kiefer… - … on Machine Learning, 2022‏ - proceedings.mlr.press
While message-passing graph neural networks have clear limitations in approximating
permutation-equivariant functions over graphs or general relational data, more expressive …