dynnode2vec: Scalable Dynamic Network Embedding

TL;DR

dynnode2vec is a scalable method for dynamic network embedding that efficiently updates node representations over time by leveraging previous embeddings and evolving random walks, addressing limitations of static methods.

Contribution

It introduces dynnode2vec, a novel dynamic embedding approach based on node2vec, capable of capturing evolving network patterns efficiently.

Findings

Outperforms static embedding methods on dynamic datasets

Reduces computational cost by initializing with previous embeddings

Effectively captures temporal network evolution

Abstract

Network representation learning in low dimensional vector space has attracted considerable attention in both academic and industrial domains. Most real-world networks are dynamic with addition/deletion of nodes and edges. The existing graph embedding methods are designed for static networks and they cannot capture evolving patterns in a large dynamic network. In this paper, we propose a dynamic embedding method, dynnode2vec, based on the well-known graph embedding method node2vec. Node2vec is a random walk based embedding method for static networks. Applying static network embedding in dynamic settings has two crucial problems: 1) Generating random walks for every time step is time consuming 2) Embedding vector spaces in each timestamp are different. In order to tackle these challenges, dynnode2vec uses evolving random walks and initializes the current graph embedding with previous embedding vectors. We demonstrate the advantages of the proposed dynamic network embedding by conducting empirical evaluations on several large dynamic network datasets.