Coden: Efficient Temporal Graph Neural Networks for Continuous Prediction

Temporal Graph Neural Networks (TGNNs) are pivotal in processing dynamic graphs. However, existing TGNNs primarily target one-time predictions for a given temporal span, whereas many practical applications require continuous predictions, that predictions are issued frequently over time. Directly adapting existing TGNNs to continuous-prediction scenarios introduces either significant computational overhead or prediction quality issues especially for large graphs. This paper revisits the challenge of continuous predictions in TGNNs, and introduces Coden, a TGNN model designed for efficient and effective learning on dynamic graphs. Coden innovatively overcomes the key complexity bottleneck in existing TGNNs while preserving comparable predictive accuracy. Moreover, we further provide theoretical analyses that substantiate the effectiveness and efficiency of Coden, and clarify its duality relationship with both RNN-based and attention-based models. Our evaluations across five dynamic datasets show that Coden surpasses existing performance benchmarks in both efficiency and effectiveness, establishing it as a superior solution for continuous prediction in evolving graph environments.