Mogilipalepu, KK and Modukuri, SK and Madapu, A and Chepuri, SP (2021) Federated Deep Unfolding for Sparse Recovery. In: European Signal Processing Conference, 23 - 27 August 2021, Dublin, pp. 1950-1954.
|
PDF
EUSIPCO_2021.pdf - Published Version Download (1MB) | Preview |
Abstract
This paper proposes a federated learning technique for deep algorithm unfolding with applications to sparse signal recovery and compressed sensing. We refer to this architecture as Fed-CS. Specifically, we unfold and learn the iterative shrinkage thresholding algorithm for sparse signal recovery without transporting the training data distributed across many clients to a central location. We propose a layer-wise federated learning technique, in which each client uses local data to train a common model. Then we transmit only the model parameters of that layer from all the clients to the server, which aggregates these local models to arrive at a consensus model. The proposed layer-wise federated learning for sparse recovery is communication efficient and preserves data privacy. Through numerical experiments on synthetic and real datasets, we demonstrate Fed-CS's efficacy and present various trade-offs in terms of the number of participating clients and communications involved compared to a centralized approach of deep unfolding.
| Item Type: | Conference Paper |
|---|---|
| Publication: | European Signal Processing Conference |
| Publisher: | European Signal Processing Conference, EUSIPCO |
| Additional Information: | The copyright for this article belongs to the Authors. |
| Keywords: | Data privacy; Deep learning; Economic and social effects; Iterative methods; Learning algorithms; Recovery; Signal reconstruction, Algorithmic unrolling; Algorithmics; Compressed-Sensing; Distributed learning; Federated learning; Layer-wise; Learning techniques; Sparse recovery; Sparse signal recoveries; Unfoldings, Compressed sensing |
| Department/Centre: | Division of Electrical Sciences > Electrical Communication Engineering Division of Interdisciplinary Sciences > Computational and Data Sciences |
| Date Deposited: | 23 May 2023 04:17 |
| Last Modified: | 23 May 2023 04:17 |
| URI: | https://eprints.iisc.ac.in/id/eprint/81724 |
Actions (login required)
 |
View Item |
