SOURCE-LINKED INTELLIGENCE

CacheDyG: Decoupling Temporal Propagation for Efficient Dynamic Graph Learning

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Dynamic graphs are widely used to model time-evolving relational systems in real-world applications. Dynamic graph neural networks provide an effective framework for capturing both structural dependencies and temporal dynamics in such data. However, they typically intertwine temporal graph propagation with every optimization epoch and often maintain large trainable representations for each node-time pair. This design repeatedly recomputes largely unchanged historical structures, leading to substantial training and parameter overhead. To address this critical issue, we propose CacheDyG, a Cache

Read original source ↗ Open in workspace

recordType

paper

region

Global