Joint Pre-Equalization and Receiver Combining Design for Federated Learning With Misaligned Over-the-Air Computation
With the growth of terminal devices and data traffic, privacy concerns have inspired an innovative edge learning framework, called federated learning (FL). Over-the-air computation (OAC) has been introduced to reduce communication overhead for FL, however, requires stringent time alignment. Misalign...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Open Journal of the Communications Society |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10302307/ |
_version_ | 1797530167003840512 |
---|---|
author | Jianda Wang Shuaishuai Guo |
author_facet | Jianda Wang Shuaishuai Guo |
author_sort | Jianda Wang |
collection | DOAJ |
description | With the growth of terminal devices and data traffic, privacy concerns have inspired an innovative edge learning framework, called federated learning (FL). Over-the-air computation (OAC) has been introduced to reduce communication overhead for FL, however, requires stringent time alignment. Misaligned OAC has been proposed by recent research where the symbol-timing misaligned superimposed signal can be recovered via whitening matched filtering and sampling (WMFS), followed by maximum likelihood (ML) estimation. Similarly to aligned OAC, misaligned OAC also suffers from the straggler issue, leading to FL’s poor performance under low EsN0. To solve this issue, we propose a novel framework of misaligned OAC FL for accurate model aggregation on wireless networks. First, we analyze the effect of aggregation error on the convergence of FL. Then, we formulate an optimization problem to minimize the distortion of the aggregation measured by mean square error (MSE) w.r.t. the transmitter equalization and receiver combining. Finally, a successive convex approximation (SCA)-based optimization algorithm is further developed to solve the resulting quadratic constrained quadratic programming. Comprehensive experiments show that the proposed algorithm achieves substantial learning performance improvement compared to existing baseline schemes and achieves the near-optimal performance of the ideal benchmark with aligned and noiseless aggregation. |
first_indexed | 2024-03-10T10:25:08Z |
format | Article |
id | doaj.art-1b6e7cb8150348e0b0c331851ae9ffb9 |
institution | Directory Open Access Journal |
issn | 2644-125X |
language | English |
last_indexed | 2024-03-10T10:25:08Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Open Journal of the Communications Society |
spelling | doaj.art-1b6e7cb8150348e0b0c331851ae9ffb92023-11-22T00:01:44ZengIEEEIEEE Open Journal of the Communications Society2644-125X2023-01-0142881289610.1109/OJCOMS.2023.332893110302307Joint Pre-Equalization and Receiver Combining Design for Federated Learning With Misaligned Over-the-Air ComputationJianda Wang0https://orcid.org/0009-0003-6217-644XShuaishuai Guo1https://orcid.org/0000-0003-0885-7327School of Control Science and Engineering, Shandong University, Jinan, ChinaSchool of Control Science and Engineering, Shandong University, Jinan, ChinaWith the growth of terminal devices and data traffic, privacy concerns have inspired an innovative edge learning framework, called federated learning (FL). Over-the-air computation (OAC) has been introduced to reduce communication overhead for FL, however, requires stringent time alignment. Misaligned OAC has been proposed by recent research where the symbol-timing misaligned superimposed signal can be recovered via whitening matched filtering and sampling (WMFS), followed by maximum likelihood (ML) estimation. Similarly to aligned OAC, misaligned OAC also suffers from the straggler issue, leading to FL’s poor performance under low EsN0. To solve this issue, we propose a novel framework of misaligned OAC FL for accurate model aggregation on wireless networks. First, we analyze the effect of aggregation error on the convergence of FL. Then, we formulate an optimization problem to minimize the distortion of the aggregation measured by mean square error (MSE) w.r.t. the transmitter equalization and receiver combining. Finally, a successive convex approximation (SCA)-based optimization algorithm is further developed to solve the resulting quadratic constrained quadratic programming. Comprehensive experiments show that the proposed algorithm achieves substantial learning performance improvement compared to existing baseline schemes and achieves the near-optimal performance of the ideal benchmark with aligned and noiseless aggregation.https://ieeexplore.ieee.org/document/10302307/Federated learningmultiple access channelsover-the-air computationasynchronouspre-equalizationreceiver combining |
spellingShingle | Jianda Wang Shuaishuai Guo Joint Pre-Equalization and Receiver Combining Design for Federated Learning With Misaligned Over-the-Air Computation IEEE Open Journal of the Communications Society Federated learning multiple access channels over-the-air computation asynchronous pre-equalization receiver combining |
title | Joint Pre-Equalization and Receiver Combining Design for Federated Learning With Misaligned Over-the-Air Computation |
title_full | Joint Pre-Equalization and Receiver Combining Design for Federated Learning With Misaligned Over-the-Air Computation |
title_fullStr | Joint Pre-Equalization and Receiver Combining Design for Federated Learning With Misaligned Over-the-Air Computation |
title_full_unstemmed | Joint Pre-Equalization and Receiver Combining Design for Federated Learning With Misaligned Over-the-Air Computation |
title_short | Joint Pre-Equalization and Receiver Combining Design for Federated Learning With Misaligned Over-the-Air Computation |
title_sort | joint pre equalization and receiver combining design for federated learning with misaligned over the air computation |
topic | Federated learning multiple access channels over-the-air computation asynchronous pre-equalization receiver combining |
url | https://ieeexplore.ieee.org/document/10302307/ |
work_keys_str_mv | AT jiandawang jointpreequalizationandreceivercombiningdesignforfederatedlearningwithmisalignedovertheaircomputation AT shuaishuaiguo jointpreequalizationandreceivercombiningdesignforfederatedlearningwithmisalignedovertheaircomputation |