用时空曲率稀疏动态图，80%删边仍保性能，提速超55%。
Edge Sparsification via Temporal Forman-Ricci Curvature for Dynamic Graph Learning
- 基于时空曲率设计边稀疏化策略，融合结构、时间与局部竞争机制。
- 在9个交易网络上实现约80%的边稀疏，推理训练时间平均减少55.94%。
- 适合大规模动态图学习，尤其对实时性要求高的金融与社交网络场景。
时序图学习对分析持续演化的现实系统（如金融交易网络、通信系统、在线社交平台）至关重要，但大规模密集且快速变化的时序图仍存在计算挑战。为此，我们提出一种基于网络曲率的边稀疏化框架，名为TRicci。该方法将经典Forman-Ricci曲率扩展至有向加权时序图，捕捉结构支持度、时间新近性及局部交互竞争关系。在9个交易网络和3个时序图基准数据集上的实验表明，该框架在多个图级预测任务中保持了良好的预测性能。结果表明，TRicci可实现约80%的边稀疏化，同时使端到端下游训练与推理时间平均减少55.94%，且预测性能无显著下降。研究说明，时序曲率可作为可扩展时序图学习的理论基础，在大幅稀疏化下仍能保留关键的时序-结构信息。
原文摘要 · Abstract (English)
Temporal graph learning has become essential for analyzing real-world systems whose interactions continuously evolve over time, including financial transaction networks, communication systems, and online social platforms. However, learning from large-scale temporal graphs remains computationally challenging when networks are dense and rapidly changing. To address this limitation, we propose a network-curvature-inspired edge sparsification framework for dynamic graph learning. Our proposed method, TRicci, extends classical Forman-Ricci curvature to directed weighted temporal graphs by capturing structural support, temporal recency, and local interaction competition. Experiments on 9 transaction networks and 3 temporal graph benchmark datasets demonstrate that the proposed framework preserves predictive performance across multiple graph-level prediction tasks. The results show that TRicci sparsifies temporal graphs by approximately 80% while reducing end-to-end downstream training and inference time by an average of 55.94%, without substantial degradation in predictive performance. Our findings suggest that temporal curvature can serve as a principled basis for scalable temporal graph learning by preserving predictive temporal-structural information under substantial sparsification.
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。