Generalization error of graph neural networks in the mean-field regime
This work provides a theoretical framework for assessing the generalization error of graph neural networks in the over-parameterized regime, where the number of parameters surpasses the quantity of data points. We explore two widely utilized types of graph neural networks: graph convolutional neural...
Main Authors: | Aminian, G, He, Y, Reinert, G, Szpruch, L, Cohen, S |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Proceedings of Machine Learning Research
2024
|
Similar Items
-
MSGNN: a spectral graph neural network based on a novel magnetic signed Laplacian
by: He, Y, et al.
Published: (2022) -
GNNRank: learning global rankings from pairwise comparisons via directed graph neural networks
by: He, Y, et al.
Published: (2022) -
Graph neural networks for network analysis
by: He, Y
Published: (2024) -
Mutual information of neural network initialisations: mean field approximations
by: Tanner, J, et al.
Published: (2021) -
Proximal mean-field for neural network quantization
by: Ajanthan, T, et al.
Published: (2020)