Manifold Filter-Combine Networks

by   Joyce Chew, et al.

We introduce a class of manifold neural networks (MNNs) that we call Manifold Filter-Combine Networks (MFCNs), that aims to further our understanding of MNNs, analogous to how the aggregate-combine framework helps with the understanding of graph neural networks (GNNs). This class includes a wide variety of subclasses that can be thought of as the manifold analog of various popular GNNs. We then consider a method, based on building a data-driven graph, for implementing such networks when one does not have global knowledge of the manifold, but merely has access to finitely many sample points. We provide sufficient conditions for the network to provably converge to its continuum limit as the number of sample points tends to infinity. Unlike previous work (which focused on specific graph constructions), our rate of convergence does not directly depend on the number of filters used. Moreover, it exhibits linear dependence on the depth of the network rather than the exponential dependence obtained previously. Additionally, we provide several examples of interesting subclasses of MFCNs and of the rates of convergence that are obtained under specific graph constructions.


page 1

page 2

page 3

page 4


A Convergence Rate for Manifold Neural Networks

High-dimensional data arises in numerous applications, and the rapidly d...

Discriminability of Single-Layer Graph Neural Networks

Network data can be conveniently modeled as a graph signal, where data v...

Geometric Graph Filters and Neural Networks: Limit Properties and Discriminability Trade-offs

This paper studies the relationship between a graph neural network (GNN)...

When Does A Spectral Graph Neural Network Fail in Node Classification?

Spectral Graph Neural Networks (GNNs) with various graph filters have re...

Stability of Manifold Neural Networks to Deformations

Stability is an important property of graph neural networks (GNNs) which...

Denoising and Interior Detection Problems

Let ℳ be a compact manifold of ℝ^d. The goal of this paper is to decide,...

Please sign up or login with your details

Forgot password? Click here to reset