Abstract The Weisfeiler–Lehman graph kernel exhibits competitive performance in many graph classification tasks. However, its subtree features are not able to capture connected …
Q Zhao, Y Wang - Advances in neural information …, 2019 - proceedings.neurips.cc
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 …
L O'Bray, B Rieck, K Borgwardt - Proceedings of the 27th ACM SIGKDD …, 2021 - dl.acm.org
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 …
D Zhou, B Schölkopf - ICML 2004 Workshop on Statistical Relational …, 2004 - pure.mpg.de
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 …