arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.12613cs.LG
收藏

Coden: 为连续预测设计的高效时序图神经网络

Coden: Efficient Temporal Graph Neural Networks for Continuous Prediction

College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学)

Zulun Zhu, Siqiang Luo

AI总结:

Coden是一种为连续预测设计的高效时序图神经网络,通过克服现有模型的复杂性瓶颈,实现了动态图的高效学习和预测。

摘要:

时序图神经网络(TGNNs)在处理动态图中至关重要。然而,现有TGNNs主要针对给定时间跨度的一次性预测,而许多实际应用需要连续预测,即在时间上频繁发出预测。直接将现有TGNNs适应到连续预测场景中,会引入显著的计算开销或预测质量问题,尤其是对于大规模图。本文重新审视TGNNs中的连续预测挑战,并引入Coden,一种为动态图高效且有效学习设计的TGNN模型。Coden创新性地克服了现有TGNNs中的关键复杂性瓶颈,同时保持了可比的预测准确性。此外,我们进一步提供了理论分析,证明了Coden的有效性和效率,并澄清了其与基于RNN和注意力机制模型的双重关系。在五个动态数据集上的评估表明,Coden在效率和有效性上均超越现有性能基准,确立了其在演变图环境中的连续预测中的优越解决方案。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑