PRISM: A Training System to Unlock the Potential of Temporal Graph Learning Through Staleness Avoidance

Training memory-augmented Temporal Graph Neural Networks (M-TGNNs) efficiently and accurately remains challenging due to memory staleness , which arises when temporally dependent events are processed in the same batch and severely degrades accuracy at large batch sizes. We introduce PRISM, an M-TGNN training system that achieves staleness-freedom without giving up GPU parallelism by using multi-versioned memory vectors , so that each event in a batch can consume the memory version that is temporally consistent for it. PRISM formalizes a relaxed notion of staleness-freedom called lazy freshness , which allows for more parallelism than existing staleness-free approaches, and implements it through a multi-versioned memory refinement algorithm over a lightweight memory computation graph. On five temporal-graph benchmarks and three M-TGNN models (TGN, TNCN, APAN), PRISM improves the accuracy of existing models by up to 28% and surpasses the TGB leaderboard by 9.2%, while keeping training time competitive with parallel stale-memory systems (TGL, ETC) and consistently lower than stricter staleness-free baselines. PRISM thus provides a practical, staleness-free foundation for temporal graph learning.