发表机构
University of Manitoba; University of Central Florida（曼尼托巴大学; 中佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对动态图学习中大规模时序图计算挑战，提出TRicci框架，通过时序Forman-Ricci曲率实现边稀疏化，可在保持预测性能的同时缩短训练推理时间。
AI 中文摘要
时序图学习对于分析随时间持续演化交互的现实系统至关重要，包括金融交易网络、通信系统和在线社交平台。然而，当网络密集且快速变化时，从大规模时序图中学习仍面临计算挑战。为解决这一局限，我们提出一种受网络曲率启发的动态图学习边稀疏化框架，命名为TRicci，它将经典Forman-Ricci曲率扩展至带权有向时序图，以捕捉结构支撑、时序新近性和局部交互竞争。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预测性能；结果显示，TRicci可将时序图稀疏化约80%，同时将端到端下游训练与推理时间平均缩短55.94%，且预测性能未出现大幅下降。我们的发现表明，时序曲率可作为可扩展时序图学习的合理基础，能在大幅稀疏化下保留预测性时序结构信息。
英文摘要
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.
