关于时序图学习算法泛化能力的理论研究与一种更简单的方法
On the Generalization Capability of Temporal Graph Learning Algorithms: Theoretical Insights and a Simpler Method
AI总结:
本文从理论上分析了时序图学习算法的泛化误差与层数/步数及特征-标签对齐分数的关系,并据此提出更简单且性能更优的Simplified-Temporal-Graph-Network。
摘要:
时序图学习(TGL)已成为各种现实应用中的一种普遍技术,尤其是在数据可以表示为图并随时间演化的领域。尽管TGL最近在算法解决方案上取得了显著进展,但其理论基础在很大程度上仍未得到探索。本文旨在通过研究不同TGL算法(例如基于GNN、基于RNN和基于记忆的方法)在有限宽度过参数化机制下的泛化能力来弥合这一差距。我们建立了TGL算法的泛化误差与基于GNN/RNN的TGL方法中“层数/步数”以及“特征-标签对齐(FLA)分数”之间的联系,其中FLA可以作为表达能力的代理指标,并解释了基于记忆方法的性能。在我们的理论分析指导下,我们提出了Simplified-Temporal-Graph-Network,它具有较小的泛化误差、更好的整体性能和更低的模型复杂度。在真实世界数据集上的大量实验证明了我们方法的有效性。我们的理论发现和所提出的算法从理论角度为TGL提供了重要见解,为未来研究中设计实用的TGL算法奠定了基础。
英文摘要:
Temporal Graph Learning (TGL) has become a prevalent technique across diverse real-world applications, especially in domains where data can be represented as a graph and evolves over time. Although TGL has recently seen notable progress in algorithmic solutions, its theoretical foundations remain largely unexplored. This paper aims at bridging this gap by investigating the generalization ability of different TGL algorithms (e.g., GNN-based, RNN-based, and memory-based methods) under the finite-wide over-parameterized regime. We establish the connection between the generalization error of TGL algorithms and "the number of layers/steps" in the GNN-/RNN-based TGL methods and "the feature-label alignment (FLA) score", where FLA can be used as a proxy for the expressive power and explains the performance of memory-based methods. Guided by our theoretical analysis, we propose Simplified-Temporal-Graph-Network, which enjoys a small generalization error, improved overall performance, and lower model complexity. Extensive experiments on real-world datasets demonstrate the effectiveness of our method. Our theoretical findings and proposed algorithm offer essential insights into TGL from a theoretical standpoint, laying the groundwork for the designing practical TGL algorithms in future studies.
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。