paper-with-me

홈 › Papers

Generalization Error of Graph Neural Networks in the Mean-field Regime

2024-02-10 · Gholamali Aminian, Yixuan He, Gesine Reinert, Łukasz Szpruch, Samuel N. Cohen

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 networks and message passing graph neural networks. Prior to this study, existing bounds on the generalization error in the over-parametrized regime were uninformative, limiting our understanding of over-parameterized network performance. Our novel approach involves deriving upper bounds within the mean-field regime for evaluating the generalization error of these graph neural networks. We establish upper bounds with a convergence rate of $O(1/n)$, where $n$ is the number of graph samples. These upper bounds offer a theoretical assurance of the networks' performance on unseen data in the challenging over-parameterized regime and overall contribute to our understanding of their performance.

📄 PDF Abstract BibTeX arXiv:2402.07025

Code (1)

sherylhyx/gnn_mf_ge 공식 구현 pytorch

Tasks

Graph Classification

Similar Papers 제목 키워드 기반

Generalization of Scaled Deep ResNets in the Mean-Field Regime

2024-03-14 · Yihang Chen, Fanghui Liu, Yiping Lu, Grigorios G. Chrysos 외

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate \emph{scaled} ResNet in the limit of infi…

Generalization Bounds

Mean-field Analysis of Generalization Errors

2023-06-20 · Gholamali Aminian, Samuel N. Cohen, Łukasz Szpruch

We propose a novel framework for exploring weak and $L_2$ generalization errors of algorithms through the lens of differential calculus on the space of probability measures. Specifically, we consider the KL-regularized e…

Simultaneous analysis of approximate leave-one-out cross-validation and mean-field inference

2025-01-05 · Pierre C Bellec

Approximate Leave-One-Out Cross-Validation (ALO-CV) is a method that has been proposed to estimate the generalization error of a regularized estimator in the high-dimensional regime where dimension and sample size are of…

Understanding Transfer Learning via Mean-field Analysis

2024-10-22 · Gholamali Aminian, Łukasz Szpruch, Samuel N. Cohen

We propose a novel framework for exploring generalization errors of transfer learning through the lens of differential calculus on the space of probability measures. In particular, we consider two main transfer learning …

Transfer Learning

The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes

2022-12-23 · Alexander Atanasov, Blake Bordelon, Sabarish Sainathan, Cengiz Pehlevan

For small training set sizes $P$, the generalization error of wide neural networks is well-approximated by the error of an infinite width neural network (NN), either in the kernel or mean-field/feature-learning regime. H…

regression