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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICASSP39728.2021.9414093 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
Graph signal processing, optimization algorithm, deep learning, signal denoising, deep algorithm unrolling | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Masatoshi Nagahama | 1 | 0 | 0.68 |
Koki Yamada | 2 | 0 | 1.69 |
Yuichi Tanaka | 3 | 158 | 50.27 |
Stanley H. Chan | 4 | 403 | 30.95 |
Y. C. Eldar | 5 | 6399 | 458.37 |