Contrastive Representation Learning for Dynamic Link Prediction in Temporal Networks

TL;DR

This paper introduces a self-supervised contrastive learning approach using recurrent message-passing neural networks for dynamic link prediction in discrete-time temporal networks, improving accuracy over existing models.

Contribution

It presents a novel contrastive training framework with combined loss functions for better representation learning in temporal networks, focusing on discrete-time data.

Findings

Outperforms existing models on Enron, COLAB, and Facebook datasets.

Self-supervised losses enhance training and prediction accuracy.

Recurrent message-passing neural network effectively models information flow.

Abstract

Evolving networks are complex data structures that emerge in a wide range of systems in science and engineering. Learning expressive representations for such networks that encode their structural connectivity and temporal evolution is essential for downstream data analytics and machine learning applications. In this study, we introduce a self-supervised method for learning representations of temporal networks and employ these representations in the dynamic link prediction task. While temporal networks are typically characterized as a sequence of interactions over the continuous time domain, our study focuses on their discrete-time versions. This enables us to balance the trade-off between computational complexity and precise modeling of the interactions. We propose a recurrent message-passing neural network architecture for modeling the information flow over time-respecting paths of temporal networks. The key feature of our method is the contrastive training objective of the model, which is a combination of three loss functions: link prediction, graph reconstruction, and contrastive predictive coding losses. The contrastive predictive coding objective is implemented using infoNCE losses at both local and global scales of the input graphs. We empirically show that the additional self-supervised losses enhance the training and improve the model's performance in the dynamic link prediction task. The proposed method is tested on Enron, COLAB, and Facebook datasets and exhibits superior results compared to existing models.