no code implementations • 12 Feb 2024 • William Leeney, Ryan McConville
Although modularity is a graph partitioning quality metric, we show that this can be used to optimise GNNs that also encode features without a drop in performance.
no code implementations • 14 Dec 2023 • William Leeney, Ryan McConville
Federated Learning is machine learning in the context of a network of clients whilst maintaining data residency and/or privacy constraints.
no code implementations • 14 Dec 2023 • William Leeney, Ryan McConville
(1) The enhanced capability of Graph Neural Networks (GNNs) in unsupervised community detection of clustered nodes is attributed to their capacity to encode both the connectivity and feature information spaces of graphs.
no code implementations • 10 May 2023 • William Leeney, Ryan McConville
We find that by ensuring the same evaluation criteria is followed, there may be significant differences from the reported performance of methods at this task, but a more complete evaluation and comparison of methods is possible.