Classification on Large Networks: A Quantitative Bound via Motifs and Graphons

10/24/2017
by   Andreas Haupt, et al.
0

When each data point is a large graph, graph statistics such as densities of certain subgraphs (motifs) can be used as feature vectors for machine learning. While intuitive, motif counts are expensive to compute and difficult to work with theoretically. Via graphon theory, we give an explicit quantitative bound for the ability of motif homomorphisms to distinguish large networks under both generative and sampling noise. Furthermore, we give similar bounds for the graph spectrum and connect it to homomorphism densities of cycles. This results in an easily computable classifier on graph data with theoretical performance guarantee. Our method yields competitive results on classification tasks for the autoimmune disease Lupus Erythematosus.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/08/2021

Scaling up graph homomorphism for classification via sampling

Feature generation is an open topic of investigation in graph machine le...
research
11/02/2017

Bootstrapping Exchangeable Random Graphs

We introduce two new bootstraps for exchangeable random graphs. One, the...
research
06/22/2022

Agent-based Graph Neural Networks

We present a novel graph neural network we call AgentNet, which is desig...
research
12/21/2017

How Well Can Generative Adversarial Networks Learn Densities: A Nonparametric View

We study in this paper the rate of convergence for learning densities un...
research
06/05/2018

Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease

Graphs are widely used as a natural framework that captures interactions...
research
02/11/2019

On the number of pancake stacks requiring 4 flips to be sorted

Using an existing classification results for the 7- and 8-cycles in the ...
research
06/09/2023

Expectation-Complete Graph Representations with Homomorphisms

We investigate novel random graph embeddings that can be computed in exp...

Please sign up or login with your details

Forgot password? Click here to reset