Information-Theoretic Thresholds for Bipartite Latent-Space Graphs under Noisy Observations

2026-02-11

AI Summary

This work addresses the problem of accurately detecting latent geometric structure in bipartite Gaussian random geometric graphs under random edge masking. The authors propose a novel Fourier-analytic framework based on power series approximations of characteristic functions, which effectively exploits cancellation effects in signed subgraph counts to substantially enlarge the class of tractable subgraphs. For the first time, they establish tight information-theoretic detectability thresholds in terms of the ambient dimension \(d\) and the masking parameter \(q\) under fixed edge density, demonstrating that detection becomes significantly easier when the mask is known. Their approach improves upon the Fourier coefficient bounds established in STOC'24 for dense bipartite graphs, extending them to sparse and non-bipartite settings while ruling out any computational–statistical gap.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Security and Privacy: Large-scale security measurements
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

We study information-theoretic phase transitions for the detectability of latent geometry in bipartite random geometric graphs RGGs with Gaussian d-dimensional latent vectors while only a subset of edges carries latent information determined by a random mask with i.i.d. Bern(q) entries. For any fixed edge density p in (0,1) we determine essentially tight thresholds for this problem as a function of d and q. Our results show that the detection problem is substantially easier if the mask is known upfront compared to the case where the mask is hidden. Our analysis is built upon a novel Fourier-analytic framework for bounding signed subgraph counts in Gaussian random geometric graphs that exploits cancellations which arise after approximating characteristic functions by an appropriate power series. The resulting bounds are applicable to much larger subgraphs than considered in previous work which enables tight information-theoretic bounds, while the bounds considered in previous works only lead to lower bounds from the lens of low-degree polynomials. As a consequence we identify the optimal information-theoretic thresholds and rule out computational-statistical gaps. Our bounds further improve upon the bounds on Fourier coefficients of random geometric graphs recently given by Bangachev and Bresler [STOC'24] in the dense, bipartite case. The techniques also extend to sparser and non-bipartite settings, at least if the considered subgraphs are sufficiently small. We furhter believe that they might help resolve open questions for related detection problems.

Problem

• latent geometry
• bipartite random geometric graphs
• information-theoretic thresholds
• noisy observations
• detectability

Innovation

• Fourier-analytic framework
• information-theoretic thresholds
• bipartite random geometric graphs
• signed subgraph counts
• computational-statistical gap