Minimax Synthesis of Network Mechanisms

2026-06-14

AI Summary

This study addresses the challenge of identifying and quantifying the contributions of multiple coexisting generative mechanisms—such as community structure, hubs, and clustering—from a single observed network. Treating the network as a composition of candidate mechanisms, the authors jointly estimate mechanism strengths and their combination rules through a framework integrating mechanism calibration and bias correction, and propose an unbiased estimator to yield valid confidence intervals. Theoretical analysis reveals a sharp threshold in graph density: only sufficiently dense networks allow unambiguous distinction between additive and interactive combinations of mechanisms. Building on minimax estimation theory, the work establishes matching convergence rates for both known- and unknown-mechanism settings. Simulations confirm the method’s validity, while real-network analyses recover established structures and use confidence intervals to rule out positive contributions from specific candidate mechanisms.

Abstract

A single observed network reflects several mechanisms at once: communities, hubs, and clustering coexist in one graph, each a different model. We treat the network as a combination of candidate mechanisms and study, from a single graph, how strongly each mechanism contributes and how they combine. We address two questions. The first is how to measure each mechanism's contribution when the mechanisms must themselves be estimated from the graph: fitting the mechanisms and their strengths from the same data biases the strengths toward zero, and a correction removes this bias and yields valid confidence intervals. The second is whether the rule of combination is itself recoverable: when a graph is generated by two mechanisms acting together, the graph alone determines whether they combine additively or interact, exactly when the graph is dense enough, a sharp threshold below which no test can decide. The estimate calibrates the candidate mechanisms against the observed edges. We establish matching minimax rate, against a known-design benchmark and the estimated-design problem itself, confirm the methods in simulation, and apply them to real networks, where the signed coefficients recover known structure and, in one case, a confidence interval excludes any positive contribution from a candidate mechanism.

Problem

• network mechanisms
• minimax synthesis
• mechanism contribution
• combination rule
• graph structure

Innovation

• minimax rate
• network mechanisms
• bias correction
• combination rule recovery
• graph density threshold