UAI 2023poster4 citations
Studying the Effect of GNN Spatial Convolutions On The Embedding Space’s Geometry
Abstract
By recursively summing node features over entire neighborhoods, spatial graph convolution operators have been heralded as key to the success of Graph Neural Networks (GNNs). Yet, despite the multiplication of GNN methods across tasks and applications, the effect of this aggregation operation has yet to be analyzed. In fact, while most recent efforts in the GNN community have focused on optimizing the architecture of the neural network, fewer works have attempted to characterize
BibTeX
@InProceedings{pmlr-v216-donnat23a,
title = {Studying the Effect of {GNN} Spatial Convolutions On The Embedding Space’s Geometry},
author = {Donnat, Claire and Jeong, So Won},
booktitle = {Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence},
pages = {539--548},
year = {2023},
editor = {Evans, Robin J. and Shpitser, Ilya},
volume = {216},
series = {Proceedings of Machine Learning Research},
month = {31 Jul--04 Aug},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v216/donnat23a/donnat23a.pdf},
url = {https://proceedings.mlr.press/v216/donnat23a.html},
abstract = {By recursively summing node features over entire neighborhoods, spatial graph convolution operators have been heralded as key to the success of Graph Neural Networks (GNNs). Yet, despite the multiplication of GNN methods across tasks and applications, the effect of this aggregation operation has yet to be analyzed. In fact, while most recent efforts in the GNN community have focused on optimizing the architecture of the neural network, fewer works have attempted to characterize