Generative Temporal Link Prediction via Self-tokenized Sequence Modeling

TL;DR

This paper introduces GLSM, a generative sequence model with self-tokenization for predicting future links in evolving networks, outperforming existing methods on real-world datasets.

Contribution

The paper proposes a novel generative link prediction model with a self-tokenization mechanism that enhances pattern discovery and generalization in temporal networks.

Findings

GLSM achieves 2-10% higher AUC than state-of-the-art methods.

The self-tokenization mechanism improves model generalization.

GLSM effectively predicts future links in five real-world datasets.

Abstract

We formalize networks with evolving structures as temporal networks and propose a generative link prediction model, Generative Link Sequence Modeling (GLSM), to predict future links for temporal networks. GLSM captures the temporal link formation patterns from the observed links with a sequence modeling framework and has the ability to generate the emerging links by inferring from the probability distribution on the potential future links. To avoid overfitting caused by treating each link as a unique token, we propose a self-tokenization mechanism to transform each raw link in the network to an abstract aggregation token automatically. The self-tokenization is seamlessly integrated into the sequence modeling framework, which allows the proposed GLSM model to have the generalization capability to discover link formation patterns beyond raw link sequences. We compare GLSM with the existing state-of-art methods on five real-world datasets. The experimental results demonstrate that GLSM obtains future positive links effectively in a generative fashion while achieving the best performance (2-10\% improvements on AUC) among other alternatives.