用自相关机制捕捉时间图中的周期性依赖，提升长期关系建模能力。
TGFormer: Towards Temporal Graph Transformer with Auto-Correlation Mechanism
- 基于时间序列分析构建轨迹框架，系统分析节点历史交互
- 自相关机制在子交互层面发现周期性依赖，精度提升最高达9.35%
- 适合需要建模复杂时序动态的图神经网络研究者使用
Temporal Graph Neural Networks (TGNNs) 因能建模复杂动态而备受关注，但其在捕捉长期依赖和识别周期模式方面存在根本挑战。为此，我们提出 TGFormer，一种专为时间图设计的新型 Transformer 架构。该模型通过轨迹框架重构时间图学习，借鉴时间序列分析原理，系统分析节点历史交互，实现对节点关系在时序上的细粒度刻画。基于随机过程理论，我们设计了自相关机制，系统挖掘节点交互中的周期性依赖。该机制使 TGFormer 能在子交互层级完成依赖发现与表征聚合，相比传统注意力机制更具效率与准确性。在六个公开基准上的实验验证了方法的有效性，相较现有最优方法，精度最高提升 9.35%。
原文摘要 · Abstract (English)
The growing interest in Temporal Graph Neural Networks (TGNNs) stems from their ability to model complex dynamics and deliver superior performance. However, TGNNs encounter fundamental challenges in capturing long-term dependencies and identifying periodic patterns. To address these limitations, we propose TGFormer, a novel Transformer architecture specifically designed for temporal graphs. Our model redefines temporal graph learning by establishing a trajectory framework that aligns with time series analysis principles. This approach allows TGFormer to derive node representations through systematic analysis of historical interactions, enabling granular examination of node relationships across sequential timestamps. Building upon stochastic process theory, we develop an auto-correlation mechanism that systematically uncovers periodic dependencies in node interactions. This innovation empowers TGFormer to perform dependency discovery and representation aggregation at sub-interaction levels, demonstrating superior efficiency and accuracy compared to conventional attention mechanisms. Experimental validation across six public benchmarks confirms the effectiveness of our approach, with TGFormer at most achieving 9.35\% precision improvement compared to state-of-the-art approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。