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 …
k-core: Theories and applications
YX Kong, GY Shi, RJ Wu, YC Zhang - Physics Reports, 2019 - Elsevier
With the rapid development of science and technology, the world is becoming increasingly
connected. The following dire need for understanding both the relationships amongst …
connected. The following dire need for understanding both the relationships amongst …
Weisfeiler and leman go neural: Higher-order graph neural networks
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 …
architecture to learn vector representations of nodes and graphs in a supervised, end-to-end …
Simgnn: A neural network approach to fast graph similarity computation
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 …
the chemical compounds that are most similar to a query compound. Graph …
Weisfeiler and leman go sparse: Towards scalable higher-order graph embeddings
Graph kernels based on the $1 $-dimensional Weisfeiler-Leman algorithm and
corresponding neural architectures recently emerged as powerful tools for (supervised) …
corresponding neural architectures recently emerged as powerful tools for (supervised) …
Speqnets: Sparsity-aware permutation-equivariant graph networks
While message-passing graph neural networks have clear limitations in approximating
permutation-equivariant functions over graphs or general relational data, more expressive …
permutation-equivariant functions over graphs or general relational data, more expressive …
The core decomposition of networks: Theory, algorithms and applications
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 …
applications in real-life problems. Simply stated, the core decomposition of a network …
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 …
An overview of distance and similarity functions for structured data
S Ontañón - Artificial Intelligence Review, 2020 - Springer
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 …
and artificial intelligence in general, since they can serve as an organizing principle by …
Wasserstein embedding for graph learning
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 …
framework for embedding entire graphs in a vector space, in which various machine …