提升时序图神经网络的位置编码效率与效果，解决计算慢、理论不清等问题。
Understanding and Improving Laplacian Positional Encodings For Temporal GNNs
- 建立超拉普拉斯编码与逐时间片编码的理论联系，揭示时间连通性优势
- 提出新方法使运行速度提升56倍，支持5万节点大规模图计算
- 实验证明编码在特定模型和任务中效果显著，但并非通用增益
时序图学习在推荐系统、交通预测和社会网络分析中有广泛应用。尽管已有多种架构提出，时序图位置编码的研究进展仍有限。通过超拉普拉斯扩展静态拉普拉斯特征向量方法虽有前景，但面临高特征分解成本、理论理解不足以及应用时机不明确等挑战。本文提出：(1) 建立超拉普拉斯编码与逐时间片编码的理论框架，揭示利用额外时间连通性的优势；(2) 提出新方法降低计算开销，在保持精度前提下实现最高56倍加速，可处理含5万活跃节点的图；(3) 开展全面实验，识别哪些模型、任务和数据集最受益于该编码。结果表明，位置编码在某些场景下能显著提升性能，但其有效性因模型而异。
原文摘要 · Abstract (English)
Temporal graph learning has applications in recommendation systems, traffic forecasting, and social network analysis. Although multiple architectures have been introduced, progress in positional encoding for temporal graphs remains limited. Extending static Laplacian eigenvector approaches to temporal graphs through the supra-Laplacian has shown promise, but also poses key challenges: high eigendecomposition costs, limited theoretical understanding, and ambiguity about when and how to apply these encodings. In this paper, we address these issues by (1) offering a theoretical framework that connects supra-Laplacian encodings to per-time-slice encodings, highlighting the benefits of leveraging additional temporal connectivity, (2) introducing novel methods to reduce the computational overhead, achieving up to 56x faster runtimes while scaling to graphs with 50,000 active nodes, and (3) conducting an extensive experimental study to identify which models, tasks, and datasets benefit most from these encodings. Our findings reveal that while positional encodings can significantly boost performance in certain scenarios, their effectiveness varies across different models.
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。