2 citations · 4 across the 6 of their papers we have counts for
Showing 2023 · cs.LGShow all
3 papers · 2 filters
cs.LG2023
Distilling Influences to Mitigate Prediction Churn in Graph Neural Networks
Andreas Roth, Thomas Liebig
Models with similar performances exhibit significant disagreement in the predictions of individual samples, referred to as prediction churn. Our work explores this phenomenon in gr…
cs.LG2023★ 2 cited
Curvature-based Pooling within Graph Neural Networks
Cedric Sanders, Andreas Roth, Thomas Liebig
Over-squashing and over-smoothing are two critical issues, that limit the capabilities of graph neural networks (GNNs). While over-smoothing eliminates the differences between node…
cs.LG2023
Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks
Andreas Roth, Thomas Liebig
Our study reveals new theoretical insights into over-smoothing and feature over-correlation in graph neural networks. Specifically, we demonstrate that with increased depth, node r…