提出高效异构时序图神经网络，提升推理速度与精度。
Simple and Efficient Heterogeneous Temporal Graph Neural Network
- 将时序建模融入空间学习，用动态注意力机制保留历史信息。
- 相比最优基线提速10倍，同时保持最高预测准确率。
- 结合大模型提示，自动捕捉节点类型隐含特征，适合复杂图数据建模。
异构时序图（HTGs）在现实世界中普遍存在。近年来，众多基于注意力的神经网络被提出以增强对HTGs的表示学习能力。然而，现有方法依赖解耦的时空学习范式，削弱了时空信息的交互，导致模型复杂度高。为此，我们提出一种新型学习范式——简单高效的异构时序图神经网络（SE-HTGNN）。具体而言，通过创新的动态注意力机制，将时序建模融入空间学习，保留历史图快照中的注意力信息以指导后续计算，从而提升整体判别性表示学习能力。此外，为全面自适应理解HTGs，我们利用大语言模型提示SE-HTGNN，使模型能捕获节点类型的隐含属性作为先验知识。大量实验表明，SE-HTGNN在保持最佳预测准确率的同时，相较最新基线实现高达10倍的速度提升。
原文摘要 · Abstract (English)
Heterogeneous temporal graphs (HTGs) are ubiquitous data structures in the real world. Recently, to enhance representation learning on HTGs, numerous attention-based neural networks have been proposed. Despite these successes, existing methods rely on a decoupled temporal and spatial learning paradigm, which weakens interactions of spatio-temporal information and leads to a high model complexity. To bridge this gap, we propose a novel learning paradigm for HTGs called Simple and Efficient Heterogeneous Temporal Graph N}eural Network (SE-HTGNN). Specifically, we innovatively integrate temporal modeling into spatial learning via a novel dynamic attention mechanism, which retains attention information from historical graph snapshots to guide subsequent attention computation, thereby improving the overall discriminative representations learning of HTGs. Additionally, to comprehensively and adaptively understand HTGs, we leverage large language models to prompt SE-HTGNN, enabling the model to capture the implicit properties of node types as prior knowledge. Extensive experiments demonstrate that SE-HTGNN achieves up to 10x speed-up over the state-of-the-art and latest baseline while maintaining the best forecasting accuracy.
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。