arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.11313eess.SPcs.LGcs.SI
收藏

通过图神经网络恢复时变信号

Time-varying Signals Recovery via Graph Neural Networks

University of Delaware(特拉华大学);La Rochelle Université(拉罗谢尔大学);Université Paris-Saclay(巴黎萨克雷大学);CentraleSupélec(巴黎中央理工-高等电力学院);Inria(法国国家信息与自动化研究所);Télécom Paris(巴黎电信学院);Institut Polytechnique de Paris(巴黎理工学院);Jadavpur University(贾达普大学)

Jhon A. Castro-Correa, Jhony H. Giraldo, Anindya Mondal, Mohsen Badiey, Thierry Bouwmans, Fragkiskos D. Malliaros

AI总结:

针对时变图信号恢复中时间差分平滑先验可能失效的问题,提出采用编码器-解码器架构、结合均方误差与 Sobolev 平滑损失的 TimeGNN,并在真实数据集上取得有竞争力的性能。

摘要:

时变图信号的恢复是一个基础性问题,在传感器网络和时间序列预测中有着大量应用。有效捕捉这些信号中的时空信息对于下游任务至关重要。以往研究将此类图信号时间差分的平滑性作为初始假设。然而,当该先验不成立时,这种平滑性假设可能导致相应应用中的性能下降。在本工作中,我们通过引入一个学习模块来放宽这一假设要求。我们提出了一种用于恢复时变图信号的时间图神经网络(Time Graph Neural Network,TimeGNN)。我们的算法采用编码器-解码器架构,并使用由均方误差函数和 Sobolev 平滑算子组成的专用损失函数。TimeGNN 在真实数据集上展现出与以往方法相比具有竞争力的性能。

英文摘要:

The recovery of time-varying graph signals is a fundamental problem with numerous applications in sensor networks and forecasting in time series. Effectively capturing the spatio-temporal information in these signals is essential for the downstream tasks. Previous studies have used the smoothness of the temporal differences of such graph signals as an initial assumption. Nevertheless, this smoothness assumption could result in a degradation of performance in the corresponding application when the prior does not hold. In this work, we relax the requirement of this hypothesis by including a learning module. We propose a Time Graph Neural Network (TimeGNN) for the recovery of time-varying graph signals. Our algorithm uses an encoder-decoder architecture with a specialized loss composed of a mean squared error function and a Sobolev smoothness operator.TimeGNN shows competitive performance against previous methods in real datasets.

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。

↑