Dynamic Graph Embedding Through Hub-aware Random Walks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tomčić, Aleksandar, Savić, Miloš, Simić, Dušan, Radovanović, Miloš
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908461677150208
author Tomčić, Aleksandar
Savić, Miloš
Simić, Dušan
Radovanović, Miloš
author_facet Tomčić, Aleksandar
Savić, Miloš
Simić, Dušan
Radovanović, Miloš
contents The role of high-degree nodes, or hubs, in shaping graph dynamics and structure is well-recognized in network science, yet their influence remains underexplored in the context of dynamic graph embedding. Recent advances in representation learning for graphs have shown that random walk-based methods can capture both structural and temporal patterns, but often overlook the impact of hubs on walk trajectories and embedding stability. In this paper, we introduce DeepHub, a method for dynamic graph embedding that explicitly integrates hub sensitivity into random walk sampling strategies. Focusing on dynnode2vec as a representative dynamic embedding method, we systematically analyze the effect of hub-biased walks across nine real-world temporal networks. Our findings reveal that standard random walks tend to overrepresent hub nodes, leading to embeddings that underfit the evolving local context of less-connected nodes. By contrast, hub-aware walks can balance exploration, resulting in embeddings that better preserve temporal neighborhood structure and improve downstream task performance. These results suggest that hub-awareness is an important yet overlooked factor in dynamic graph embedding, and our work provides a foundation for more robust, structure-sensitive representation learning in evolving networks.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17764
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dynamic Graph Embedding Through Hub-aware Random Walks
Tomčić, Aleksandar
Savić, Miloš
Simić, Dušan
Radovanović, Miloš
Social and Information Networks
The role of high-degree nodes, or hubs, in shaping graph dynamics and structure is well-recognized in network science, yet their influence remains underexplored in the context of dynamic graph embedding. Recent advances in representation learning for graphs have shown that random walk-based methods can capture both structural and temporal patterns, but often overlook the impact of hubs on walk trajectories and embedding stability. In this paper, we introduce DeepHub, a method for dynamic graph embedding that explicitly integrates hub sensitivity into random walk sampling strategies. Focusing on dynnode2vec as a representative dynamic embedding method, we systematically analyze the effect of hub-biased walks across nine real-world temporal networks. Our findings reveal that standard random walks tend to overrepresent hub nodes, leading to embeddings that underfit the evolving local context of less-connected nodes. By contrast, hub-aware walks can balance exploration, resulting in embeddings that better preserve temporal neighborhood structure and improve downstream task performance. These results suggest that hub-awareness is an important yet overlooked factor in dynamic graph embedding, and our work provides a foundation for more robust, structure-sensitive representation learning in evolving networks.
title Dynamic Graph Embedding Through Hub-aware Random Walks
topic Social and Information Networks
url https://arxiv.org/abs/2505.17764