Graph Signal Denoising Using Nested-Structured Deep Algorithm Unrolling

Masatoshi Nagahama, Koki Yamada, Yuichi Tanaka, Stanley H. Chan, Yonina C. EldarICASSP 2021 · OpenReview

Abstract

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.
BibTeX
@inproceedings{nagahama2021graph,
  author = {Masatoshi Nagahama and Koki Yamada and Yuichi Tanaka and Stanley H. Chan and Yonina C. Eldar},
  title = {{Graph Signal Denoising Using Nested-Structured Deep Algorithm Unrolling}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2021},
  url = {https://openreview.net/forum?id=STbU7kkCRBu},
}

Loading related content...

Figure