paper-with-me

Papers

Generalization Bounds for Message Passing Networks on Mixture of Graphons

2024-04-04 · Sohir Maskey, Gitta Kutyniok, Ron Levie

We study the generalization capabilities of Message Passing Neural Networks (MPNNs), a prevalent class of Graph Neural Networks (GNN). We derive generalization bounds specifically for MPNNs with normalized sum aggregation and mean aggregation. Our analysis is based on a data generation model incorporating a finite set of template graphons. Each graph within this framework is generated by sampling from one of the graphons with a certain degree of perturbation. In particular, we extend previous MPNN generalization results to a more realistic setting, which includes the following modifications: 1) we analyze simple random graphs with Bernoulli-distributed edges instead of weighted graphs; 2) we sample both graphs and graph signals from perturbed graphons instead of clean graphons; and 3) we analyze sparse graphs instead of dense graphs. In this more realistic and challenging scenario, we provide a generalization bound that decreases as the average number of nodes in the graphs increases. Our results imply that MPNNs with higher complexity than the size of the training set can still generalize effectively, as long as the graphs are sufficiently large.

📄 PDF Abstract BibTeX arXiv:2404.03473

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization Bounds

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
MPNN There are at least eight notable examples of models from the literature that can be described using the Message Passing Neural Networks (MPNN) framework. For simplicity we…

Similar Papers 제목 키워드 기반

A Note on Graphon-Signal Analysis of Graph Neural Networks

2025-08-25 · Levi Rauchwerger, Ron Levie arxiv

A recent paper, ``A Graphon-Signal Analysis of Graph Neural Networks'', by Levie, analyzed message passing graph neural networks (MPNNs) by embedding the input space of MPNNs, i.e., attributed graphs (graph-signals), to …

Generalization and Representational Limits of Graph Neural Networks

2020-02-14 · ICML 2020 1 · Vikas K. Garg, Stefanie Jegelka, Tommi Jaakkola

We address two fundamental questions about graph neural networks (GNNs). First, we prove that several important graph properties cannot be computed by GNNs that rely entirely on local information. Such GNNs include the s…

Generalization Bounds

A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks

2020-12-14 · ICLR 2021 1 · Renjie Liao, Raquel Urtasun, Richard Zemel

In this paper, we derive generalization bounds for the two primary classes of graph neural networks (GNNs), namely graph convolutional networks (GCNs) and message passing GNNs (MPGNNs), via a PAC-Bayesian approach. Our r…

Generalization Bounds

Gates

2008-12-01 · NeurIPS 2008 12 · Tom Minka, John Winn

Gates are a new notation for representing mixture models and context-sensitive independence in factor graphs. Factor graphs provide a natural representation for message-passing algorithms, such as expectation propagation…

Higher-Order Graphon Neural Networks: Approximation and Cut Distance

2025-03-18 · Daniel Herbst, Stefanie Jegelka

Graph limit models, like graphons for limits of dense graphs, have recently been used to study size transferability of graph neural networks (GNNs). While most literature focuses on message passing GNNs (MPNNs), in this …