File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/GLOBECOM46510.2021.9685788
- WOS: WOS:000790747204026
Supplementary
-
Citations:
- Web of Science: 0
- Appears in Collections:
Conference Paper: Unit-Modulus Wireless Federated Learning Via Penalty Alternating Minimization
Title | Unit-Modulus Wireless Federated Learning Via Penalty Alternating Minimization |
---|---|
Authors | |
Issue Date | 2021 |
Citation | 2021 IEEE Global Communications Conference (GLOBECOM) How to Cite? |
Abstract | Wireless federated learning (FL) is an emerging machine learning paradigm that trains a global parametric model from distributed datasets via wireless communications. This paper proposes a unit-modulus wireless FL (UMWFL) framework, which simultaneously uploads local model parameters and computes global model parameters via optimized phase shifting. The proposed framework avoids sophisticated baseband signal processing, leading to both low communication delays and implementation costs. A training loss bound is derived and a penalty alternating minimization (PAM) algorithm is proposed to minimize the nonconvex nonsmooth loss bound. Experimental results in the Car Learning to Act (CARLA) platform show that the proposed UMWFL framework with PAM algorithm achieves smaller training losses and testing errors than those of the benchmark scheme. |
Persistent Identifier | http://hdl.handle.net/10722/320907 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, S | - |
dc.contributor.author | Li, D | - |
dc.contributor.author | Wang, R | - |
dc.contributor.author | Hao, Q | - |
dc.contributor.author | Wu, YC | - |
dc.contributor.author | Ng, D | - |
dc.date.accessioned | 2022-11-01T04:43:29Z | - |
dc.date.available | 2022-11-01T04:43:29Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | 2021 IEEE Global Communications Conference (GLOBECOM) | - |
dc.identifier.uri | http://hdl.handle.net/10722/320907 | - |
dc.description.abstract | Wireless federated learning (FL) is an emerging machine learning paradigm that trains a global parametric model from distributed datasets via wireless communications. This paper proposes a unit-modulus wireless FL (UMWFL) framework, which simultaneously uploads local model parameters and computes global model parameters via optimized phase shifting. The proposed framework avoids sophisticated baseband signal processing, leading to both low communication delays and implementation costs. A training loss bound is derived and a penalty alternating minimization (PAM) algorithm is proposed to minimize the nonconvex nonsmooth loss bound. Experimental results in the Car Learning to Act (CARLA) platform show that the proposed UMWFL framework with PAM algorithm achieves smaller training losses and testing errors than those of the benchmark scheme. | - |
dc.language | eng | - |
dc.relation.ispartof | 2021 IEEE Global Communications Conference (GLOBECOM) | - |
dc.title | Unit-Modulus Wireless Federated Learning Via Penalty Alternating Minimization | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Wu, YC: ycwu@eee.hku.hk | - |
dc.identifier.authority | Wu, YC=rp00195 | - |
dc.identifier.doi | 10.1109/GLOBECOM46510.2021.9685788 | - |
dc.identifier.hkuros | 341157 | - |
dc.identifier.isi | WOS:000790747204026 | - |