Search Results for author: Andreas Roth

Found 6 papers, 3 papers with code

Distilling Influences to Mitigate Prediction Churn in Graph Neural Networks

no code implementations2 Oct 2023 Andreas Roth, Thomas Liebig

Our work explores this phenomenon in graph neural networks by investigating differences between models differing only in their initializations in their utilized features for predictions.

Knowledge Distillation Node Classification

Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks

1 code implementation31 Aug 2023 Andreas Roth, Thomas Liebig

Our study reveals new theoretical insights into over-smoothing and feature over-correlation in deep graph neural networks.

Curvature-based Pooling within Graph Neural Networks

1 code implementation31 Aug 2023 Cedric Sanders, Andreas Roth, Thomas Liebig

CurvPool exploits the notion of curvature of a graph to adaptively identify structures responsible for both over-smoothing and over-squashing.

Graph Classification

Forecasting Unobserved Node States with spatio-temporal Graph Neural Networks

no code implementations21 Nov 2022 Andreas Roth, Thomas Liebig

Our framework can be combined with any spatio-temporal Graph Neural Network, that exploits spatio-temporal correlations with surrounding observed locations by using the network's graph structure.

Graph Neural Network Inductive Bias

Transforming PageRank into an Infinite-Depth Graph Neural Network

1 code implementation1 Jul 2022 Andreas Roth, Thomas Liebig

Popular graph neural networks are shallow models, despite the success of very deep architectures in other application domains of deep learning.

Graph Classification Graph Neural Network

Medley2K: A Dataset of Medley Transitions

no code implementations25 Aug 2020 Lukas Faber, Sandro Luck, Damian Pascual, Andreas Roth, Gino Brunner, Roger Wattenhofer

The automatic generation of medleys, i. e., musical pieces formed by different songs concatenated via smooth transitions, is not well studied in the current literature.

Cannot find the paper you are looking for? You can Submit a new open access paper.