Embeddings of Nation-Level Social Networks

2026-03-30

AI Summary

This study addresses the challenge of dynamic node embedding in large-scale, multilayer, time-varying social networks at the national level by leveraging a population-scale social network of the Netherlands. The work proposes three key technical contributions: a hierarchy-aware random walk strategy that effectively captures cross-layer structural information; a future-leak-free annual temporal alignment method that ensures temporal consistency; and an enhanced embedding distribution achieved through Fibonacci spiral sampling combined with embedding whitening, which improves both uniformity and representational capacity. Evaluated across thirteen downstream tasks, the proposed approach significantly outperforms existing baselines, demonstrating its effectiveness and strong generalization capability.

Abstract

Full nation-scale social networks are now emerging from countries such as the Netherlands and Denmark, but these networks present challenging technical issues in working with large, multiplex, time-dependent networks. We report on our experiences in producing dynamic node embeddings of the population network of the Netherlands. We present (a) a layer-sensitive random walk strategy which improves on traditional flattening methods for multiplex networks, (b) a temporal alignment strategy that brings annual networks into the same embedding space, without leaking information to future years, and (c) the use of Fibonacci spirals and embedding whitening techniques for more balanced and effective partitioning. We demonstrate the effectiveness of these techniques in building embedding-based models for 13 downstream tasks.

Problem

• social networks
• node embeddings
• multiplex networks
• temporal networks
• large-scale networks

Innovation

• layer-sensitive random walk
• temporal alignment
• embedding whitening
• Fibonacci spirals
• multiplex network embeddings