MANIFOLD FILTERS AND NEURAL NETWORKS: GEOMETRIC GRAPH SIGNAL PROCESSING IN THE LIMIT

Loading...
Thumbnail Image
Degree type
PhD
Graduate group
Electrical and Systems Engineering
Discipline
Electrical Engineering
Subject
Graph neural networks
Graph signal processing
Manifold neural networks
Spectral analysis
Funder
Grant number
License
Copyright date
01/01/2025
Distributor
Related resources
Author
Wang, Zhiyang
Contributor
Abstract

Graph Neural Networks (GNNs) are the tool of choice for scalable and stable learning in graph-structured data applications involving geometric information. In this thesis, we address the fundamental questions of how GNNs can generalize across different graph scales and how they can remain stable on large-scale graphs. We do so by considering manifolds as graph limit models. Specifically, we explain how to build manifold convolutional filters and manifold neural networks (MNNs) as the limit objects of graph convolutional filters and GNNs when the graphs are sampled from manifolds. Using the Laplace-Beltrami operator exponentials to define manifold convolutions, we demonstrate their algebraic equivalence to both graph convolutions and standard time convolutions in nodal and spectral domains. This equivalence provides a unifying framework to analyze key theoretical properties of GNNs: i) Convergence of GNNs to MNNs allows the scalability of GNNs on graphs across scales. ii) The stability of MNNs to deformations indicates the stability of large-scale GNNs. These findings offer practical guidelines for designing GNN architectures, particularly by imposing constraints on the spectral properties of filter functions. This framework provides a unique perspective from signal processing to interpret the behavior of GNNs. The practical guidance indicated by the theoretical results is verified in real-world scenarios, including point cloud analysis, wireless resource allocation, and wind field studies on vector fields.

Advisor
Ribeiro, Alejandro
Date of degree
2025
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation