Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graph
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911411879280640 |
|---|---|
| author | Duc, Nguyen Minh Ta, Viet Cuong |
| author_facet | Duc, Nguyen Minh Ta, Viet Cuong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_23233 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graph Duc, Nguyen Minh Ta, Viet Cuong Machine Learning 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. |
| title | Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graph |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.23233 |