Graph kernels have become an established and widely-used technique for solving
classification tasks on graphs. This survey gives a comprehensive overview of techniques …

Omnipresent network/graph data generally have the characteristics of nonlinearity,
sparseness, dynamicity and heterogeneity, which bring numerous challenges to network …

Abstract Graph Neural Networks (GNNs) are limited in their expressive power, struggle with
long-range interactions and lack a principled way to model higher-order structures. These …

The pairwise interaction paradigm of graph machine learning has predominantly governed
the modelling of relational systems. However, graphs alone cannot capture the multi-level …

Graph neural network (GNN)'s success in graph classification is closely related to the
Weisfeiler-Lehman (1-WL) algorithm. By iteratively aggregating neighboring node features …

While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of
applications, recent studies exposed important shortcomings in their ability to capture the …

Abstract Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to
measure the expressive power of graph neural networks (GNN). It was shown that the …

Link prediction is a key problem for network-structured data. Link prediction heuristics use
some score functions, such as common neighbors and Katz index, to measure the likelihood …

Neural networks are typically designed to deal with data in tensor forms. In this paper, we
propose a novel neural network architecture accepting graphs of arbitrary structure. Given a …

Mixup is an advanced data augmentation method for training neural network based image
classifiers, which interpolates both features and labels of a pair of images to produce …