Robust Dynamic Network Embedding via Ensembles

TL;DR

This paper introduces a robust ensemble-based dynamic network embedding method that maintains high performance across networks with varying degrees of change, outperforming existing methods in effectiveness and scalability.

Contribution

It proposes a novel ensemble approach with diverse base learners for more robust dynamic network embedding, addressing the limitations of existing methods under different network change conditions.

Findings

The proposed method outperforms state-of-the-art DNE methods in robustness and effectiveness.

Ensemble diversity enhances embedding quality across different degrees of network change.

The method demonstrates scalability to large dynamic networks.

Abstract

Dynamic Network Embedding (DNE) has recently attracted considerable attention due to the advantage of network embedding in various fields and the dynamic nature of many real-world networks. An input dynamic network to DNE is often assumed to have smooth changes over snapshots, which however would not hold for all real-world scenarios. It is natural to ask if existing DNE methods can perform well for an input dynamic network without smooth changes. To quantify it, an index called Degree of Changes (DoCs) is suggested so that the smaller DoCs indicates the smoother changes. Our comparative study shows several DNE methods are not robust enough to different DoCs even if the corresponding input dynamic networks come from the same dataset, which would make these methods unreliable and hard to use for unknown real-world applications. To propose an effective and more robust DNE method, we follow the notion of ensembles where each base learner adopts an incremental Skip-Gram embedding model. To further boost the performance, a simple yet effective strategy is designed to enhance the diversity among base learners at each timestep by capturing different levels of local-global topology. Extensive experiments demonstrate the superior effectiveness and robustness of the proposed method compared to state-of-the-art DNE methods, as well as the benefits of special designs in the proposed method and its scalability.