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...
Prif Awduron: | Aminian, G, He, Y, Reinert, G, Szpruch, L, Cohen, S |
---|---|
Fformat: | Conference item |
Iaith: | English |
Cyhoeddwyd: |
Proceedings of Machine Learning Research
2024
|
Eitemau Tebyg
-
MSGNN: a spectral graph neural network based on a novel magnetic signed Laplacian
gan: He, Y, et al.
Cyhoeddwyd: (2022) -
GNNRank: learning global rankings from pairwise comparisons via directed graph neural networks
gan: He, Y, et al.
Cyhoeddwyd: (2022) -
Graph neural networks for network analysis
gan: He, Y
Cyhoeddwyd: (2024) -
GDRMA: Graph Neural Networks for Document Retrievals With Mean Aggregation
gan: Shigeru Maya
Cyhoeddwyd: (2024-01-01) -
Physics-Informed Graph Neural Operator for Mean Field Games on Graph: A Scalable Learning Approach
gan: Xu Chen, et al.
Cyhoeddwyd: (2024-03-01)