Graph Signal Denoising Using Nested-Structured Deep Algorithm Unrolling
Graph Signal Denoising Using Nested-Structured Deep Algorithm Unrolling
复制标题
DOI：
10.1109/icassp39728.2021.9414093
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Masatoshi Nagahama;Koki Yamada;Yuichi Tanaka;Stanley H. Chan;Y. Eldar
中科院分区：
文献类型：
--
作者：
Masatoshi Nagahama;Koki Yamada;Yuichi Tanaka;Stanley H. Chan;Y. Eldar
在本文中，我们提出了一种基于交替方向乘法器（ADMM）的一种变体的深度算法展开（DAU），称为即插即用ADMM (PnP-ADMM)，用于图上信号的去噪。DAU是一种可训练的深度架构，通过对现有优化算法的展开迭代实现，该算法在每一层都包含可训练的参数。我们还提出了一个嵌套结构的DAU：其展开迭代中的子模块也是由DAU设计的。在社区图和美国温度数据上的合成信号上进行了几个图信号去噪实验，以验证所提出的方法。我们提出的方法优于其他基于优化和深度学习的方法。
In this paper, we propose a deep algorithm unrolling (DAU) based on a variant of the alternating direction method of multiplier (ADMM) called Plug-and-Play ADMM (PnP-ADMM) for denoising of signals on graphs. DAU is a trainable deep architecture realized by unrolling iterations of an existing optimization algorithm which contains trainable parameters at each layer. We also propose a nested-structured DAU: Its submodules in the unrolled iterations are also designed by DAU. Several experiments for graph signal denoising are performed on synthetic signals on a community graph and U.S. temperature data to validate the proposed approach. Our proposed method outperforms alternative optimization- and deep learning-based approaches.