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

With the rapid development of science and technology, the world is becoming increasingly
connected. The following dire need for understanding both the relationships amongst …

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 …

Graph similarity search is among the most important graph-based applications, eg finding
the chemical compounds that are most similar to a query compound. Graph …

Graph kernels based on the $1 $-dimensional Weisfeiler-Leman algorithm and
corresponding neural architectures recently emerged as powerful tools for (supervised) …

While message-passing graph neural networks have clear limitations in approximating
permutation-equivariant functions over graphs or general relational data, more expressive …

The core decomposition of networks has attracted significant attention due to its numerous
applications in real-life problems. Simply stated, the core decomposition of a network …

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 …

The notions of distance and similarity play a key role in many machine learning approaches,
and artificial intelligence in general, since they can serve as an organizing principle by …

We present Wasserstein Embedding for Graph Learning (WEGL), a novel and fast
framework for embedding entire graphs in a vector space, in which various machine …