Coden: Efficient Temporal Graph Neural Networks for Continuous Prediction
This addresses the need for efficient continuous predictions in dynamic graphs, which is crucial for practical applications, though it appears incremental as it builds on existing TGNN methods.
The paper tackled the problem of continuous predictions in Temporal Graph Neural Networks (TGNNs), which existing methods handle inefficiently or with quality issues, and introduced Coden, a model that achieves superior efficiency and effectiveness, as shown by evaluations across five dynamic datasets surpassing benchmarks.
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 {\sc Coden}, a TGNN model designed for efficient and effective learning on dynamic graphs. {\sc 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 {\sc Coden}, and clarify its duality relationship with both RNN-based and attention-based models. Our evaluations across five dynamic datasets show that {\sc Coden} surpasses existing performance benchmarks in both efficiency and effectiveness, establishing it as a superior solution for continuous prediction in evolving graph environments.