aiqbench analysis
This research introduces TRicci, a method that leverages temporal Forman-Ricci curvature to sparsify dynamic graphs by roughly 80% while maintaining predictive accuracy and significantly cutting training/inference times. By extending classical curvature concepts to directed weighted temporal networks, the approach offers a principled solution for scaling graph learning on dense, evolving systems like financial transactions and social platforms. The work demonstrates that structural support and temporal recency can be effectively captured without substantial performance degradation, addressing key computational bottlenecks in real-world temporal graph analysis.
Edge Sparsification via Temporal Forman-Ricci Curvature for Dynamic Graph Learning
arXiv:2608.07158v2 Announce Type: replace Abstract: 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.
Abstract: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.
Machine Learning (cs.LG)
arXiv:2608.07158 [cs.LG]
(or arXiv:2608.07158v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.07158 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 251 words
Related coverage
Dynamic Graph Prompting via Topology-Routed Mixed-Curvature Experts
arXiv · Aug 7, 2026
Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature
arXiv · Jul 27, 2026
Discrete Ricci Curvature on Protein Contact Graphs for Lightweight Fold Classification
arXiv · Jul 21, 2026
Edgewise Envelopes Between Balanced Forman and Ollivier-Ricci Curvature
arXiv · Oct 15, 2026