ScaWL: Scaling k-WL (Weisfeiler-Lehman) Algorithms in Memory and Performance on Shared and Distributed-Memory Systems
The k-dimensional Weisfeiler-Leman (k-WL) algorithm—developed as an efficient heuristic
for testing if two graphs are isomorphic—is a fundamental kernel for node embedding in the …
for testing if two graphs are isomorphic—is a fundamental kernel for node embedding in the …
No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets
Benchmark datasets have proved pivotal to the success of graph learning, and good
benchmark datasets are crucial to guide the development of the field. Recent research has …
benchmark datasets are crucial to guide the development of the field. Recent research has …
Unsupervised Optimisation of GNNs for Node Clustering
Graph Neural Networks (GNNs) can be trained to detect communities within a graph by
learning from the duality of feature and connectivity information. Currently, the common …
learning from the duality of feature and connectivity information. Currently, the common …
Financial Networks and Other Adventures in Graph Learning
B Egressy - 2024 - research-collection.ethz.ch
This thesis investigates graph problems from both a machine learning and a theoretical
perspective. In particular, it explores financial applications, focusing on fraud detection …
perspective. In particular, it explores financial applications, focusing on fraud detection …
[PDF][PDF] Unsupervised Graph Neural Networks
W LEENEY - 2024 - research-information.bris.ac.uk
Attributed graphs are the fundamental data representation that captures the dual di-
mensionality of structural connectivity and feature information. The task of community …
mensionality of structural connectivity and feature information. The task of community …