Scholarlink

<p>Temporal graphs provide a powerful framework for modeling time-dependent interactions in dynamic systems such as social, biological, and communication graphs. Continuous-Time Dynamic Graphs (CTDGs) are commonly used to represent such graphs; however, existing approaches often fail to capture higher-order temporal motifs, limiting their effectiveness in downstream tasks. We propose a novel framework that combines temporally-biased random walks and motif-based incidence matrices to extract and encode multi-scale higher-order interaction patterns. By integrating these structural features with Node2Vec embeddings, we construct expressive node representations that jointly capture temporal and topological dynamics. Extensive experiments across five benchmark datasets demonstrate that our method consistently outperforms strong representative baselines under a unified inductive evaluation protocol, achieving improvements of up to 9.1% in AUC. Our framework is scalable, robust, and broadly applicable to real-world temporal graphs. All code and trained models are publicly released at: <a href="https://github.com/marwane-alilou/TemporalMotif-CTDG">https://github.com/marwane-alilou/TemporalMotif-CTDG</a> to foster reproducibility.8097</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Temporal motif-based representation learning on continuous-time dynamic graphs

  • 期刊论文

  • 发表日期：

    2026年3月6日

查看全文
  • Marouane Alilou,
  • Bikram Pratim Bhuyan,
  • Rachida Fissoune,
  • Amar Ramdane-Cherif

摘要

Temporal graphs provide a powerful framework for modeling time-dependent interactions in dynamic systems such as social, biological, and communication graphs. Continuous-Time Dynamic Graphs (CTDGs) are commonly used to represent such graphs; however, existing approaches often fail to capture higher-order temporal motifs, limiting their effectiveness in downstream tasks. We propose a novel framework that combines temporally-biased random walks and motif-based incidence matrices to extract and encode multi-scale higher-order interaction patterns. By integrating these structural features with Node2Vec embeddings, we construct expressive node representations that jointly capture temporal and topological dynamics. Extensive experiments across five benchmark datasets demonstrate that our method consistently outperforms strong representative baselines under a unified inductive evaluation protocol, achieving improvements of up to 9.1% in AUC. Our framework is scalable, robust, and broadly applicable to real-world temporal graphs. All code and trained models are publicly released at: https://github.com/marwane-alilou/TemporalMotif-CTDG to foster reproducibility.8097