Saved in:
Bibliographic Details
Main Authors: Qi, Tong, Andersson, Vera, Viechnicki, Peter, Lyzinski, Vince
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.02825
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912461543702528
author Qi, Tong
Andersson, Vera
Viechnicki, Peter
Lyzinski, Vince
author_facet Qi, Tong
Andersson, Vera
Viechnicki, Peter
Lyzinski, Vince
contents We present the OmniMatch algorithm for seeded multiple graph matching. In the setting of $d$-dimensional Random Dot Product Graphs (RDPG), we prove that under mild assumptions, OmniMatch with $s$ seeds asymptotically and efficiently perfectly aligns $O(s^α)$ unseeded vertices -- for $α<2\wedge d/4$ -- across multiple networks even in the presence of no edge correlation. We demonstrate the effectiveness of our algorithm across numerous simulations and in the context of shuffled graph hypothesis testing. In the shuffled testing setting, testing power is lost due to the misalignment/shuffling of vertices across graphs, and we demonstrate the capacity of OmniMatch to correct for misaligned vertices prior to testing and hence recover the lost testing power. We further demonstrate the algorithm on a pair of data examples from connectomics and machine translation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02825
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Asymptotically perfect seeded graph matching without edge correlation (and applications to inference)
Qi, Tong
Andersson, Vera
Viechnicki, Peter
Lyzinski, Vince
Machine Learning
We present the OmniMatch algorithm for seeded multiple graph matching. In the setting of $d$-dimensional Random Dot Product Graphs (RDPG), we prove that under mild assumptions, OmniMatch with $s$ seeds asymptotically and efficiently perfectly aligns $O(s^α)$ unseeded vertices -- for $α<2\wedge d/4$ -- across multiple networks even in the presence of no edge correlation. We demonstrate the effectiveness of our algorithm across numerous simulations and in the context of shuffled graph hypothesis testing. In the shuffled testing setting, testing power is lost due to the misalignment/shuffling of vertices across graphs, and we demonstrate the capacity of OmniMatch to correct for misaligned vertices prior to testing and hence recover the lost testing power. We further demonstrate the algorithm on a pair of data examples from connectomics and machine translation.
title Asymptotically perfect seeded graph matching without edge correlation (and applications to inference)
topic Machine Learning
url https://arxiv.org/abs/2506.02825