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 2401.11074cs.LG
收藏

论微分方程启发的图神经网络的时间域

On The Temporal Domain of Differential Equation Inspired Graph Neural Networks

University of Cambridge(剑桥大学);University of British Columbia(不列颠哥伦比亚大学);Ben-Gurion University of the Negev(内盖夫本-古里安大学)

Moshe Eliasof, Eldad Haber, Eran Treister, Carola-Bibiane Schönlieb

AI总结:

针对现有 DE-GNNs 仅依赖一阶或二阶时间依赖的限制,本文提出 TDE-GNN,通过神经扩展学习更广泛的时间动态,并在多个图基准上验证其优于预定义动态模型。

摘要:

图神经网络(GNNs)在建模图结构数据中的复杂关系方面已展现出显著成功。该领域最近的一项创新是微分方程启发的图神经网络(DE-GNNs)家族,它们利用连续动力系统的原理来建模图上的信息流,并具备特征平滑或保持等内置属性。然而,现有的 DE-GNNs 依赖于一阶或二阶时间依赖。在本文中,我们提出了对这些预定义时间依赖的一种神经扩展。我们表明,我们名为 TDE-GNN 的模型能够捕捉超出典型一阶或二阶方法范围的广泛时间动态,并提供了现有时间模型受到挑战的用例。我们在多个图基准上证明了使用我们的方法学习时间依赖,而非使用预定义时间动态所带来的收益。

英文摘要:

Graph Neural Networks (GNNs) have demonstrated remarkable success in modeling complex relationships in graph-structured data. A recent innovation in this field is the family of Differential Equation-Inspired Graph Neural Networks (DE-GNNs), which leverage principles from continuous dynamical systems to model information flow on graphs with built-in properties such as feature smoothing or preservation. However, existing DE-GNNs rely on first or second-order temporal dependencies. In this paper, we propose a neural extension to those pre-defined temporal dependencies. We show that our model, called TDE-GNN, can capture a wide range of temporal dynamics that go beyond typical first or second-order methods, and provide use cases where existing temporal models are challenged. We demonstrate the benefit of learning the temporal dependencies using our method rather than using pre-defined temporal dynamics on several graph benchmarks.

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。

↑