CacheDyG: Decoupling Temporal Propagation for Efficient Dynamic Graph Learning

CacheDyG introduces a cache‑refine framework that decouples temporal propagation from parameter updates in dynamic graph neural networks. By storing graph‑aware node‑time representations in non‑trainable buffers and updating only a lightweight refiner, residual gate, and link predictor during training, it reduces repeated recomputation of historical structures. Experiments on five benchmarks show that CacheDyG uses fewer trainable parameters, runs faster, and achieves competitive or better predictive performance compared to existing baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• benchmarks