Infinite Width Graph Neural Networks for Node Regression/ Classification
Abstract
This work analyzes Graph Neural Networks, a generalization of Fully-Connected Deep Neural Nets on Graph structured data, when their width, that is the number of nodes in each fullyconnected layer is increasing to infinity. Infinite Width Neural Networks are connecting Deep Learning to Gaussian Processes and Kernels, both Machine Learning Frameworks with long traditions and extensive theoretical foundations. Gaussian Processes and Kernels have much less hyperparameters then Neural Networks and can be used for uncertainty estimation, making them more user friendly for applications. This works extends the increasing amount of research connecting Gaussian Processes and Kernels to Neural Networks. The Kernel and Gaussian Process closed forms are derived for a variety of architectures, namely the standard Graph Neural Network, the Graph Neural Network with Skip-Concatenate Connections and the Graph Attention Neural Network. All architectures are evaluated on a variety of datasets on the task of transductive Node Regression and Classification. Additionally, a Spectral Sparsification method known as Effective Resistance is used to improve runtime and memory requirements. Extending the setting to inductive graph learning tasks (Graph Regression/ Classification) is straightforward and is briefly discussed in 3.5.
Cite
@article{arxiv.2310.08176,
title = {Infinite Width Graph Neural Networks for Node Regression/ Classification},
author = {Yunus Cobanoglu},
journal= {arXiv preprint arXiv:2310.08176},
year = {2023}
}
Comments
49 Pages, 2 Figures (with subfigures), multiple tables, v2: made table of contents fit to one page and added derivatives on GAT*NTK and GAT*GP in A.4, v3: shorten parts of introduction and fixed typos, added numberings to equations and discussion section, v4: fix two missing citations on page 10