Near-Perfect Recovery in the One-Dimensional Latent Space Model

Suppose a graph G is stochastically created by uniformly sampling vertices along a line segment and connecting each pair of vertices with a probability that is a known decreasing function of their distance. We ask if it is possible to reconstruct the actual positions of the vertices in G by only observing the generated unlabeled graph. We study this question for two natural edge probability functions – one where the probability of an edge decays exponentially with the distance and another where this probability decays only linearly. We initiate our study with the weaker goal of recovering only the order in which vertices appear on the line segment. For a segment of length n and a precision parameter δ, we show that for both exponential and linear decay edge probability functions, there is an efficient algorithm that correctly recovers (up to reflection symmetry) the order of all vertices that are at least δ apart, using only Õ(n/δ ^ 2) samples (vertices). Building on this result, we then show that O(n^2 log n/δ ^2) vertices (samples) are sufficient to additionally recover the location of each vertex on the line to within a precision of δ. We complement this result with an Ω (n^1.5/δ) lower bound on samples needed for reconstructing positions (even by a computationally unbounded algorithm), showing that the task of recovering positions is information-theoretically harder than recovering the order. We give experimental results showing that our algorithm recovers the positions of almost all points with high accuracy.

Authors

• 123 publications
• 9 publications
• 18 publications
07/29/2021

Improved Reconstruction of Random Geometric Graphs

Embedding graphs in a geographical or latent space, i.e., inferring loca...
07/08/2021

Sampling and Counting Edges via Vertex Accesses

We consider the problems of sampling and counting edges from a graph on ...
07/20/2017

Pictures of Combinatorial Cubes

We prove that the 8-point algorithm always fails to reconstruct a unique...
10/09/2015

Recovering a Hidden Community Beyond the Spectral Limit in O(|E| ^*|V|) Time

Community detection is considered for a stochastic block model graph of ...
06/03/2021

Efficient ℤ_2 synchronization on ℤ^d under symmetry-preserving side information

We consider ℤ_2-synchronization on the Euclidean lattice. Every vertex o...
12/11/2020

Rainbow Perfect and Near-Perfect Matchings in Complete Graphs with Edges Colored by Circular Distance

Given an edge-colored complete graph K_n on n vertices, a perfect (respe...
10/04/2021

Spiked Covariance Estimation from Modulo-Reduced Measurements

Consider the rank-1 spiked model: X=√(ν)ξu+ Z, where ν is the spike inte...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.