A survey on graph kernels
Graph kernels have become an established and widely-used technique for solving
classification tasks on graphs. This survey gives a comprehensive overview of techniques …
classification tasks on graphs. This survey gives a comprehensive overview of techniques …
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 …
kernels focus on local properties of graphs and ignore global structure. In this paper, we …
X-view: Graph-based semantic multi-view localization
A Gawel, C Del Don, R Siegwart… - IEEE Robotics and …, 2018 - ieeexplore.ieee.org
Global registration of multiview robot data is a challenging task. Appearance-based global
localization approaches often fail under drastic view-point changes, as representations have …
localization approaches often fail under drastic view-point changes, as representations have …
Graph kernels: A survey
Graph kernels have attracted a lot of attention during the last decade, and have evolved into
a rapidly developing branch of learning on structured data. During the past 20 years, the …
a rapidly developing branch of learning on structured data. During the past 20 years, the …
Redundancy-free message passing for graph neural networks
R Chen, S Zhang, Y Li - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Abstract Graph Neural Networks (GNNs) resemble the Weisfeiler-Lehman (1-WL) test, which
iteratively update the representation of each node by aggregating information from WL-tree …
iteratively update the representation of each node by aggregating information from WL-tree …
Applying graph neural networks to support decision making on collective intelligent transportation systems
ESA da Silva, H Pedrini… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Recent advancements in autonomous vehicles and vehicular ad-hoc networks (VANETs)
have presented diverse solutions for vehicle safety and automation. The demand to …
have presented diverse solutions for vehicle safety and automation. The demand to …
Tree++: Truncated tree based graph kernels
Graph-structured data arise ubiquitously in many application domains. A fundamental
problem is to quantify their similarities. Graph kernels are often used for this purpose, which …
problem is to quantify their similarities. Graph kernels are often used for this purpose, which …
Learning interpretable metric between graphs: Convex formulation and computation with graph mining
T Yoshida, I Takeuchi, M Karasuyama - Proceedings of the 25th ACM …, 2019 - dl.acm.org
Graph is a standard approach to modeling structured data. Although many machine learning
methods depend on the metric of the input objects, defining an appropriate distance function …
methods depend on the metric of the input objects, defining an appropriate distance function …
A unifying view of explicit and implicit feature maps of graph kernels
Non-linear kernel methods can be approximated by fast linear ones using suitable explicit
feature maps allowing their application to large scale problems. We investigate how …
feature maps allowing their application to large scale problems. We investigate how …
Distance metric learning for graph structured data
T Yoshida, I Takeuchi, M Karasuyama - Machine Learning, 2021 - Springer
Graphs are versatile tools for representing structured data. As a result, a variety of machine
learning methods have been studied for graph data analysis. Although many such learning …
learning methods have been studied for graph data analysis. Although many such learning …