Improving Temporal Link Prediction via Temporal Walk Matrix Projection

TL;DR

This paper introduces TPNet, a novel temporal graph neural network that unifies relative encodings with temporal walk matrices, enhancing efficiency and effectiveness in temporal link prediction tasks.

Contribution

The paper proposes a new temporal walk matrix-based encoding and a corresponding neural network, TPNet, improving computational efficiency and predictive performance in temporal link prediction.

Findings

TPNet outperforms baselines on most datasets.

Achieves up to 33.3x speedup over state-of-the-art methods.

Effectively incorporates temporal decay and structural info.

Abstract

Temporal link prediction, aiming at predicting future interactions among entities based on historical interactions, is crucial for a series of real-world applications. Although previous methods have demonstrated the importance of relative encodings for effective temporal link prediction, computational efficiency remains a major concern in constructing these encodings. Moreover, existing relative encodings are usually constructed based on structural connectivity, where temporal information is seldom considered. To address the aforementioned issues, we first analyze existing relative encodings and unify them as a function of temporal walk matrices. This unification establishes a connection between relative encodings and temporal walk matrices, providing a more principled way for analyzing and designing relative encodings. Based on this analysis, we propose a new temporal graph neural network called TPNet, which introduces a temporal walk matrix that incorporates the time decay effect to simultaneously consider both temporal and structural information. Moreover, TPNet designs a random feature propagation mechanism with theoretical guarantees to implicitly maintain the temporal walk matrices, which improves the computation and storage efficiency. Experimental results on 13 benchmark datasets verify the effectiveness and efficiency of TPNet, where TPNet outperforms other baselines on most datasets and achieves a maximum speedup of $33.3 \times$ compared to the SOTA baseline. Our code can be found at \url{https://github.com/lxd99/TPNet}.