ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2412.16457
74
1

Robust random graph matching in dense graphs via vector approximate message passing

21 December 2024
Zhangsong Li
ArXivPDFHTML
Abstract

In this paper, we focus on the matching recovery problem between a pair of correlated Gaussian Wigner matrices with a latent vertex correspondence. We are particularly interested in a robust version of this problem such that our observation is a perturbed input (A+E,B+F)(A+E,B+F)(A+E,B+F) where (A,B)(A,B)(A,B) is a pair of correlated Gaussian Wigner matrices and E,FE,FE,F are adversarially chosen matrices supported on an unknown ϵn∗ϵn\epsilon n * \epsilon nϵn∗ϵn principle minor of A,BA,BA,B, respectively. We propose a vector-approximate message passing (vector-AMP) algorithm that succeeds in polynomial time as long as the correlation ρ\rhoρ between (A,B)(A,B)(A,B) is a non-vanishing constant and ϵ=o(1(log⁡n)20)\epsilon = o\big( \tfrac{1}{(\log n)^{20}} \big)ϵ=o((logn)201​). The main methodological inputs for our result are the iterative random graph matching algorithm proposed in \cite{DL22+, DL23+} and the spectral cleaning procedure proposed in \cite{IS24+}. To the best of our knowledge, our algorithm is the first efficient random graph matching type algorithm that is robust under any adversarial perturbations of n1−o(1)n^{1-o(1)}n1−o(1) size.

View on arXiv
Comments on this paper