TempNodeEmb:Temporal Node Embedding considering temporal edge influence matrix

TL;DR

TempNodeEmb is a novel temporal node embedding method that leverages evolving network dynamics and GNNs to improve future link prediction in temporal networks, outperforming existing models.

Contribution

Introduces a new temporal node embedding technique using GNNs and Given's angle, addressing the gap in capturing temporal network evolution.

Findings

Outperforms six benchmark models in link prediction accuracy

Effective on four real-world temporal network datasets

Demonstrates the importance of temporal dynamics in node embeddings

Abstract

Understanding the evolutionary patterns of real-world evolving complex systems such as human interactions, transport networks, biological interactions, and computer networks has important implications in our daily lives. Predicting future links among the nodes in such networks reveals an important aspect of the evolution of temporal networks. To analyse networks, they are mapped to adjacency matrices, however, a single adjacency matrix cannot represent complex relationships (e.g. temporal pattern), and therefore, some approaches consider a simplified representation of temporal networks but in high-dimensional and generally sparse matrices. As a result, adjacency matrices cannot be directly used by machine learning models for making network or node level predictions. To overcome this problem, automated frameworks are proposed for learning low-dimensional vectors for nodes or edges, as state-of-the-art techniques in predicting temporal patterns in networks such as link prediction. However, these models fail to consider temporal dimensions of the networks. This gap motivated us to propose in this research a new node embedding technique which exploits the evolving nature of the networks considering a simple three-layer graph neural network at each time step, and extracting node orientation by Given's angle method. To prove our proposed algorithm's efficiency, we evaluated the efficiency of our proposed algorithm against six state-of-the-art benchmark network embedding models, on four real temporal networks data, and the results show our model outperforms other methods in predicting future links in temporal networks.