Temporal Network Representation Learning via Historical Neighborhoods Aggregation

TL;DR

This paper introduces EHNA, a novel method for learning node embeddings in evolving networks by aggregating historical neighborhoods with a temporal random walk and attention mechanism, improving network analysis tasks.

Contribution

The paper presents a new temporal random walk and attention-based deep learning model for capturing temporal information in network embeddings, addressing evolving network challenges.

Findings

Enhanced performance in link prediction tasks

Effective in network reconstruction

Outperforms existing methods on real-world datasets

Abstract

Network embedding is an effective method to learn low-dimensional representations of nodes, which can be applied to various real-life applications such as visualization, node classification, and link prediction. Although significant progress has been made on this problem in recent years, several important challenges remain, such as how to properly capture temporal information in evolving networks. In practice, most networks are continually evolving. Some networks only add new edges or nodes such as authorship networks, while others support removal of nodes or edges such as internet data routing. If patterns exist in the changes of the network structure, we can better understand the relationships between nodes and the evolution of the network, which can be further leveraged to learn node representations with more meaningful information. In this paper, we propose the Embedding via Historical Neighborhoods Aggregation (EHNA) algorithm. More specifically, we first propose a temporal random walk that can identify relevant nodes in historical neighborhoods which have impact on edge formations. Then we apply a deep learning model which uses a custom attention mechanism to induce node embeddings that directly capture temporal information in the underlying feature representation. We perform extensive experiments on a range of real-world datasets, and the results demonstrate the effectiveness of our new approach in the network reconstruction task and the link prediction task.