Search Results for author:
Found 6 papers, 3 papers with code
Transforming PageRank into an Infinite-Depth Graph Neural Network
Popular graph neural networks are shallow models, despite the success of very deep architectures in other application domains of deep learning.
Medley2K: A Dataset of Medley Transitions
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.
Forecasting Unobserved Node States with spatio-temporal Graph Neural Networks
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.
Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks
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
CurvPool exploits the notion of curvature of a graph to adaptively identify structures responsible for both over-smoothing and over-squashing.
Distilling Influences to Mitigate Prediction Churn in Graph Neural Networks
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.
