Optimality of Message-Passing Architectures for Sparse Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Baranwal, Aseem, Fountoulakis, Kimon, Jagannath, Aukosh
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910777249628160
author Baranwal, Aseem
Fountoulakis, Kimon
Jagannath, Aukosh
author_facet Baranwal, Aseem
Fountoulakis, Kimon
Jagannath, Aukosh
contents We study the node classification problem on feature-decorated graphs in the sparse setting, i.e., when the expected degree of a node is $O(1)$ in the number of nodes, in the fixed-dimensional asymptotic regime, i.e., the dimension of the feature data is fixed while the number of nodes is large. Such graphs are typically known to be locally tree-like. We introduce a notion of Bayes optimality for node classification tasks, called asymptotic local Bayes optimality, and compute the optimal classifier according to this criterion for a fairly general statistical data model with arbitrary distributions of the node features and edge connectivity. The optimal classifier is implementable using a message-passing graph neural network architecture. We then compute the generalization error of this classifier and compare its performance against existing learning methods theoretically on a well-studied statistical model with naturally identifiable signal-to-noise ratios (SNRs) in the data. We find that the optimal message-passing architecture interpolates between a standard MLP in the regime of low graph signal and a typical convolution in the regime of high graph signal. Furthermore, we prove a corresponding non-asymptotic result.
format Preprint
id arxiv_https___arxiv_org_abs_2305_10391
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Optimality of Message-Passing Architectures for Sparse Graphs
Baranwal, Aseem
Fountoulakis, Kimon
Jagannath, Aukosh
Machine Learning
We study the node classification problem on feature-decorated graphs in the sparse setting, i.e., when the expected degree of a node is $O(1)$ in the number of nodes, in the fixed-dimensional asymptotic regime, i.e., the dimension of the feature data is fixed while the number of nodes is large. Such graphs are typically known to be locally tree-like. We introduce a notion of Bayes optimality for node classification tasks, called asymptotic local Bayes optimality, and compute the optimal classifier according to this criterion for a fairly general statistical data model with arbitrary distributions of the node features and edge connectivity. The optimal classifier is implementable using a message-passing graph neural network architecture. We then compute the generalization error of this classifier and compare its performance against existing learning methods theoretically on a well-studied statistical model with naturally identifiable signal-to-noise ratios (SNRs) in the data. We find that the optimal message-passing architecture interpolates between a standard MLP in the regime of low graph signal and a typical convolution in the regime of high graph signal. Furthermore, we prove a corresponding non-asymptotic result.
title Optimality of Message-Passing Architectures for Sparse Graphs
topic Machine Learning
url https://arxiv.org/abs/2305.10391