aiqbench analysis
This paper introduces a nonparametric Weighted Random Dot Product Graph (WRDPG) model that extends standard spectral embedding techniques to handle heterogeneous edge weights. By leveraging moment-generating functions, the approach uniquely distinguishes between weight distributions sharing the same mean but differing in higher-order moments, providing rigorous statistical guarantees for node embedding and graph generation. This advancement offers a robust framework for analyzing complex network structures where edge weights carry nuanced information beyond simple connectivity.
Weighted Random Dot Product Graphs
arXiv:2505.03649v4 Announce Type: replace-cross Abstract: Modeling of intricate relational patterns has become a cornerstone of contemporary statistical research and related data science fields. Networks, represented as graphs, offer a natural framework for this analysis. This paper extends the Random Dot Product Graph (RDPG) model to accommodate weighted graphs, markedly broadening the model's scope to scenarios where edges exhibit heterogeneous weight distributions. We propose a nonparametric weighted (W)RDPG model that assigns a sequence of latent positions to each node. Inner products of these nodal vectors specify the moments of their incident edge weights' distribution via moment-generating functions. In this way, and unlike prior art, the WRDPG can discriminate between weight distributions that share the same mean but differ in other higher-order moments. We derive statistical guarantees for an estimator of the nodal's latent positions adapted from the workhorse adjacency spectral embedding, establishing its consistency and asymptotic normality. We also contribute a generative framework that enables sampling of graphs that adhere to a (prescribed or data-fitted) WRDPG, facilitating, e.g., the analysis and testing of observed graph metrics using judicious reference distributions. The paper is organized to formalize the model's definition, the estimation (or nodal embedding) process and its guarantees, as well as the methodologies for generating weighted graphs, all complemented by illustrative and reproducible examples showcasing the WRDPG's effectiveness in various network analytic applications.
Abstract:Modeling of intricate relational patterns has become a cornerstone of contemporary statistical research and related data science fields. Networks, represented as graphs, offer a natural framework for this analysis. This paper extends the Random Dot Product Graph (RDPG) model to accommodate weighted graphs, markedly broadening the model's scope to scenarios where edges exhibit heterogeneous weight distributions. We propose a nonparametric weighted (W)RDPG model that assigns a sequence of latent positions to each node. Inner products of these nodal vectors specify the moments of their incident edge weights' distribution via moment-generating functions. In this way, and unlike prior art, the WRDPG can discriminate between weight distributions that share the same mean but differ in other higher-order moments. We derive statistical guarantees for an estimator of the nodal's latent positions adapted from the workhorse adjacency spectral embedding, establishing its consistency and asymptotic normality. We also contribute a generative framework that enables sampling of graphs that adhere to a (prescribed or data-fitted) WRDPG, facilitating, e.g., the analysis and testing of observed graph metrics using judicious reference distributions. The paper is organized to formalize the model's definition, the estimation (or nodal embedding) process and its guarantees, as well as the methodologies for generating weighted graphs, all complemented by illustrative and reproducible examples showcasing the WRDPG's effectiveness in various network analytic applications.
30 pages, 12 figures, code to generate Figures 3 to 12 available at this https URL. Updated to match the published version
Machine Learning (stat.ML); Machine Learning (cs.LG); Combinatorics (math.CO); Probability (math.PR)
arXiv:2505.03649 [stat.ML]
(or arXiv:2505.03649v4 [stat.ML] for this version)
https://doi.org/10.1214/26-EJS2538 DOI(s) linking to related resources
Full text under the publisher's open licence · 263 words
Related coverage
Bell-CHSH Violation for a Massless Majorana Field in a Double Cone from Modular Localization
arXiv · Aug 26, 2026
Sharp Mixed Spectral Barron Regularity of Coulombic Many-Electron Wave Functions
arXiv · Sep 2, 2026
Learning the identity: a case study of how SGD selects among functional decompositions
arXiv · Oct 2, 2026
A Spectral Theory of Grokking: Weight Decay induces Feature Learning
arXiv · Sep 24, 2026