When Speed meets Accuracy: an Efficient and Effective Graph Model for Temporal Link Prediction

TL;DR

EAGLE is a lightweight, efficient framework for temporal link prediction that combines recent neighbor information and global structural patterns, outperforming complex models in speed and accuracy.

Contribution

The paper introduces EAGLE, a novel framework that simplifies temporal link prediction by integrating short-term and long-term information without complex computations.

Findings

EAGLE achieves over 50x speedup compared to transformer-based T-GNNs.

EAGLE outperforms state-of-the-art T-GNNs in accuracy on seven real-world datasets.

EAGLE maintains high effectiveness while significantly improving efficiency.

Abstract

Temporal link prediction in dynamic graphs is a critical task with applications in diverse domains such as social networks, recommendation systems, and e-commerce platforms. While existing Temporal Graph Neural Networks (T-GNNs) have achieved notable success by leveraging complex architectures to model temporal and structural dependencies, they often suffer from scalability and efficiency challenges due to high computational overhead. In this paper, we propose EAGLE, a lightweight framework that integrates short-term temporal recency and long-term global structural patterns. EAGLE consists of a time-aware module that aggregates information from a node's most recent neighbors to reflect its immediate preferences, and a structure-aware module that leverages temporal personalized PageRank to capture the influence of globally important nodes. To balance these attributes, EAGLE employs an adaptive weighting mechanism to dynamically adjust their contributions based on data characteristics. Also, EAGLE eliminates the need for complex multi-hop message passing or memory-intensive mechanisms, enabling significant improvements in efficiency. Extensive experiments on seven real-world temporal graphs demonstrate that EAGLE consistently achieves superior performance against state-of-the-art T-GNNs in both effectiveness and efficiency, delivering more than a 50x speedup over effective transformer-based T-GNNs.