Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graph

TL;DR

This paper introduces SDG, a sequence diffusion model that enhances temporal link prediction in dynamic graphs by capturing uncertainty and sequential structure through a generative denoising approach.

Contribution

The paper presents a novel sequence-level diffusion framework for dynamic graphs, unifying generative modeling with temporal link prediction, which improves over existing discriminative methods.

Findings

SDG achieves state-of-the-art results on multiple benchmarks.

The model effectively captures uncertainty in future link predictions.

SDG outperforms existing methods in accuracy and robustness.

Abstract

Temporal link prediction in dynamic graphs is a fundamental problem in many real-world systems. Existing temporal graph neural networks mainly focus on learning representations of historical interactions. Despite their strong performance, these models are still purely discriminative, producing point estimates for future links and lacking an explicit mechanism to capture the uncertainty and sequential structure of future temporal interactions. In this paper, we propose SDG, a novel sequence-level diffusion framework that unifies dynamic graph learning with generative denoising. Specifically, SDG injects noise into the entire historical interaction sequence and jointly reconstructs all interaction embeddings through a conditional denoising process, thereby enabling the model to capture more comprehensive interaction distributions. To align the generative process with temporal link prediction, we employ a cross-attention denoising decoder to guide the reconstruction of the destination sequence and optimize the model in an end-to-end manner. Extensive experiments on various temporal graph benchmarks show that SDG consistently achieves state-of-the-art performance in the temporal link prediction task.