Random Graph Matching in Geometric Models: the Case of Complete Graphs

02/22/2022
by   Haoyu Wang, et al.
0

This paper studies the problem of matching two complete graphs with edge weights correlated through latent geometries, extending a recent line of research on random graph matching with independent edge weights to geometric models. Specifically, given a random permutation π^* on [n] and n iid pairs of correlated Gaussian vectors {X_π^*(i), Y_i} in ℝ^d with noise parameter σ, the edge weights are given by A_ij=κ(X_i,X_j) and B_ij=κ(Y_i,Y_j) for some link function κ. The goal is to recover the hidden vertex correspondence π^* based on the observation of A and B. We focus on the dot-product model with κ(x,y)=⟨ x, y ⟩ and Euclidean distance model with κ(x,y)=x-y^2, in the low-dimensional regime of d=o(log n) wherein the underlying geometric structures are most evident. We derive an approximate maximum likelihood estimator, which provably achieves, with high probability, perfect recovery of π^* when σ=o(n^-2/d) and almost perfect recovery with a vanishing fraction of errors when σ=o(n^-1/d). Furthermore, these conditions are shown to be information-theoretically optimal even when the latent coordinates {X_i} and {Y_i} are observed, complementing the recent results of [DCK19] and [KNW22] in geometric models of the planted bipartite matching problem. As a side discovery, we show that the celebrated spectral algorithm of [Ume88] emerges as a further approximation to the maximum likelihood in the geometric model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/29/2021

Settling the Sharp Reconstruction Thresholds of Random Graph Matching

This paper studies the problem of recovering the hidden vertex correspon...
research
07/12/2021

Strong recovery of geometric planted matchings

We study the problem of efficiently recovering the matching between an u...
research
12/18/2019

The Planted Matching Problem: Phase Transitions and Exact Results

We study the problem of recovering a planted matching in randomly weight...
research
12/26/2018

Maximum Likelihood Estimation and Graph Matching in Errorfully Observed Networks

Given a pair of graphs with the same number of vertices, the inexact gra...
research
10/26/2020

Random Geometric Graphs on Euclidean Balls

We consider a latent space model for random graphs where a node i is ass...
research
04/08/2020

Graph Matching with Partially-Correct Seeds

The graph matching problem aims to find the latent vertex correspondence...
research
11/18/2019

Consistent recovery threshold of hidden nearest neighbor graphs

Motivated by applications such as discovering strong ties in social netw...

Please sign up or login with your details

Forgot password? Click here to reset