We propose an approach to learning with graph-structured data in the problem domain of
graph classification. In particular, we present a novel type of readout operation to aggregate …

Abstract The Weisfeiler–Lehman graph kernel exhibits competitive performance in many
graph classification tasks. However, its subtree features are not able to capture connected …

Recently a new feature representation and data analysis methodology based on a
topological tool called persistent homology (and its persistence diagram summary) has …

Graph neural networks (GNNs) are a powerful architecture for tackling graph learning tasks,
yet have been shown to be oblivious to eminent substructures such as cycles. We present …

This work generalizes graph neural networks (GNNs) beyond those based on the Weisfeiler-
Lehman (WL) algorithm, graph Laplacians, and diffusions. Our approach, denoted …

The two predominant approaches to graph comparison in recent years are based on (i)
enumerating matching subgraphs or (ii) comparing neighborhoods of nodes. In this work, we …

Graph learning is a popular approach for perfor ming machine learning on graph-structured
data. It has revolutionized the machine learning ability to model graph data to address …

A Regularization Framework for Learning from Graph Data Page 1 A Regularization Framework
for Learning from Graph Data Dengyong Zhou dengyong.zhou@tuebingen.mpg.de Max Planck …

Graph neural networks (GNNs) have emerged as a powerful tool for graph classification and
representation learning. However, GNNs tend to suffer from over-smoothing problems and …

Though graph representation learning (GRL) has made significant progress, it is still a
challenge to extract and embed the rich topological structure and feature information in an …