Evolving Node Embeddings for Dynamic Exploration of Network Topologies

Abstract

Static node embedding algorithms applied to snapshots of real-world applications graphs are unable to capture their evolving process. As a result, the absence of information about the dynamics in these node representations can harm the accuracy and increase processing time of machine learning tasks related to these applications. We propose a biased random walk method named Evolving Node Embedding (EVNE), which leverages the sequential relationship of graph snapshots by incorporating historic information when generating embeddings for the next snapshot. EVNE  learns node representations through a neural network, but differs from existing methods as it: (i) incorporates previously run walks at each step; (ii) starts the optimization of the current embedding from the parameters obtained in the previous iteration; and (iii) uses two time-varying parameters to regulate the behavior of the biased random walks over the process of graph exploration. Through a wide set of experiments we show that our approach generates better embeddings, outperforming baselines in a downstream node classification task.