Towards Transparent Deep Learning: Neural Precoder Design for Downlink RSMA

The non-convexity of rate-splitting precoder design precludes the direct use of efficient convex optimization algorithms. Instead, successive convex approximation (SCA)-based methods have emerged as a promising approach for precoder design in rate-splitting multiple access (RSMA) systems. Although S...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on communications p. 1
Main Authors: Wang, Chao, Li, Guo, Li, Zan, Zhang, Haibin, Jin, Liang
Format: Journal Article
Language:English
Published: IEEE 2025
Subjects:
ISSN:0090-6778, 1558-0857
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The non-convexity of rate-splitting precoder design precludes the direct use of efficient convex optimization algorithms. Instead, successive convex approximation (SCA)-based methods have emerged as a promising approach for precoder design in rate-splitting multiple access (RSMA) systems. Although SCA-based algorithms deliver satisfactory performance, their lengthy optimization process and high computational complexity-due to repeatedly solving approximate problems-hinder real-time implementation. To address this challenge, we propose an alternating direction method of multipliers (ADMM)-induced deep learning network (AIDLN)-based precoder design for multiuser downlink communications, leveraging the strengths of both model-based optimization and data-driven deep learning. Specifically, we first develop an iterative precoding algorithm based on ADMM, where each subproblem admits a closed-form solution. Next, we unfold the iterations of this ADMM-based algorithm into the layers of a neural network, constructing a deep-unfolding architecture. To accelerate convergence, we introduce trainable parameters alongside the ADMM hyperparameters. Numerical results demonstrate that our AIDLN-based precoder achieves superior performance compared to traditional model-based optimization while maintaining low computational complexity, making it suitable for real-time applications.
AbstractList The non-convexity of rate-splitting precoder design precludes the direct use of efficient convex optimization algorithms. Instead, successive convex approximation (SCA)-based methods have emerged as a promising approach for precoder design in rate-splitting multiple access (RSMA) systems. Although SCA-based algorithms deliver satisfactory performance, their lengthy optimization process and high computational complexity-due to repeatedly solving approximate problems-hinder real-time implementation. To address this challenge, we propose an alternating direction method of multipliers (ADMM)-induced deep learning network (AIDLN)-based precoder design for multiuser downlink communications, leveraging the strengths of both model-based optimization and data-driven deep learning. Specifically, we first develop an iterative precoding algorithm based on ADMM, where each subproblem admits a closed-form solution. Next, we unfold the iterations of this ADMM-based algorithm into the layers of a neural network, constructing a deep-unfolding architecture. To accelerate convergence, we introduce trainable parameters alongside the ADMM hyperparameters. Numerical results demonstrate that our AIDLN-based precoder achieves superior performance compared to traditional model-based optimization while maintaining low computational complexity, making it suitable for real-time applications.
Author Jin, Liang
Li, Guo
Wang, Chao
Li, Zan
Zhang, Haibin
Author_xml – sequence: 1
  givenname: Chao
  orcidid: 0000-0003-0187-6453
  surname: Wang
  fullname: Wang, Chao
  email: drchaowang@126.com
  organization: Integrated Service Networks Lab, Xidian University, Xi'an, China
– sequence: 2
  givenname: Guo
  orcidid: 0000-0001-6273-9028
  surname: Li
  fullname: Li, Guo
  email: liguo@stu.xidian.edu.cn
  organization: School of Cyber Engineering, Xidian University, Xi'an, China
– sequence: 3
  givenname: Zan
  orcidid: 0000-0002-5207-6504
  surname: Li
  fullname: Li, Zan
  organization: Integrated Service Networks Lab, Xidian University, Xi'an, China
– sequence: 4
  givenname: Haibin
  orcidid: 0000-0002-0080-6341
  surname: Zhang
  fullname: Zhang, Haibin
  email: hbzhang@mail.xidian.edu.cn
  organization: School of Cyber Engineering, Xidian University, Xi'an, China
– sequence: 5
  givenname: Liang
  orcidid: 0000-0001-6464-6263
  surname: Jin
  fullname: Jin, Liang
  email: liangjin@263.net
  organization: Information Engineering University, Zhengzhou, China
BookMark eNpFkNtKAzEURYNUsK3-gPiQH5h6kkwu41upV5xa0fF5iJmTMlozJakU_96pLQgH9oHN2g9rRAahC0jIOYMJY1BcVrPFfD7hwOVEKK6AiyMyZFKaDIzUAzIEKCBTWpsTMkrpAwByEGJIHqtua2OTaBVtSGsbMWzoNeKalmhjaMPyij7hd7Qr-hzRdQ3Gvk7tMlDf9W-3Das2fNKX1_n0lBx7u0p4dsgxebu9qWb3Wbm4e5hNy8wxoTaZRo7Oa-N1o0DknOXaOOV54X1ujLfevVtWMMWtsgZBskbm_RnpvLJeOTEmfL_rYpdSRF-vY_tl40_NoN7pqP901Dsd9UFHD13soRYR_wHGmSl4Ln4B6w9eBQ
CODEN IECMBT
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/TCOMM.2025.3626023
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-0857
EndPage 1
ExternalDocumentID 10_1109_TCOMM_2025_3626023
11218924
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62371357
  funderid: 10.13039/501100001809
GroupedDBID -~X
.DC
0R~
29I
4.4
5GY
6IK
85S
97E
AAJGR
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
HZ~
IES
IFIPE
IPLJI
JAVBF
LAI
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
ZCA
3EH
5VS
AAYXX
ABFSI
ACKIV
AETIX
AGSQL
AI.
AIBXA
ALLEH
CITATION
E.L
EJD
H~9
IAAWW
IBMZZ
ICLAB
IFJZH
M43
VH1
ZCG
ID FETCH-LOGICAL-c136t-7e2ecf78f7d603421478c6f29ff488fafcba19162a6a8e051d54d5485cf6af6c3
IEDL.DBID RIE
ISSN 0090-6778
IngestDate Sat Nov 29 06:58:20 EST 2025
Wed Nov 05 07:10:46 EST 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c136t-7e2ecf78f7d603421478c6f29ff488fafcba19162a6a8e051d54d5485cf6af6c3
ORCID 0000-0002-5207-6504
0000-0003-0187-6453
0000-0001-6273-9028
0000-0001-6464-6263
0000-0002-0080-6341
PageCount 1
ParticipantIDs ieee_primary_11218924
crossref_primary_10_1109_TCOMM_2025_3626023
PublicationCentury 2000
PublicationDate 2025-00-00
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 2025-00-00
PublicationDecade 2020
PublicationTitle IEEE transactions on communications
PublicationTitleAbbrev TCOMM
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0004033
Score 2.463552
Snippet The non-convexity of rate-splitting precoder design precludes the direct use of efficient convex optimization algorithms. Instead, successive convex...
SourceID crossref
ieee
SourceType Index Database
Publisher
StartPage 1
SubjectTerms alternating direction method of multipliers
Approximation algorithms
Computational complexity
Computational modeling
Covariance matrices
Deep learning
deep unfolding
Downlink
Iterative algorithms
Mathematical models
Optimization
precoder design
rate splitting multiple access
Spectral efficiency
Title Towards Transparent Deep Learning: Neural Precoder Design for Downlink RSMA
URI https://ieeexplore.ieee.org/document/11218924
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-0857
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004033
  issn: 0090-6778
  databaseCode: RIE
  dateStart: 19720101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8JAEJ4I8aAHnxjxlT14M4XSx-7WGwGJiYJEMeHWbLezxgsQKP5-Z7c14MGDSQ9NX2m-zWTm253vW4BbFaCmMkB7WkfcizCIvczniYeZ1FGYURLynVD4WYxGcjpNxpVY3WlhENE1n2HLnrq1_Hyu13aqrE21QUcSYahBTQhRirU2Ikg_rCwnbT-7kD8KGT9pT3ovwyFxwSBuWfcVPwh_ZaGtbVVcVhkc_vN_juCgKh9ZtxzvY9jB2Qnsb5kKnsLTxHXCrljpW27FXgXrIy5Y5aX6cc-sJQd9ZmzpcI5Lum37OBgVsKxv3fOJoLLXt2G3Ae-Dh0nv0au2TPB0J-SFJ5CwN0IakXNr7teJhNTcBIkxFKlGGZ0pYmg8UFxJpIDM44gOGWvDleE6PIP6bD7Dc2CZsWwqp2wWZVFGoa8Mmtxua-MbJTpJE-5-IEwXpTNG6hiFn6QO8NQCnlaAN6Fh8ds8WUF38cf1S9izr5eTHVdQL5ZrvIZd_VV8rpY3buS_AeT5q3I
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8JAEN0omqgHPzHi5x68mUI_ttvWGwEJBopEa8Kt2W5njRcgUPz9zm5L0IMHkx6attk0r53MvN15bwm5Fy5ILAOkJSXjFgPXtzKbRxZkoWRehknINkLhYTAahZNJNK7E6kYLAwCm-Qya-tSs5eczudJTZS2sDZwQCcM22fEZc51SrrWRQdpeZTqpO9qDcK2RsaNW0nmJY2SDrt_U_iu26_3KQz82VjF5pXf0zzc6JodVAUnb5Rc_IVswPSUHP2wFz8ggMb2wS1o6l2u5V0G7AHNaual-PFJtyoHDjDUhzmGBt3UnB8USlna1fz5SVPr6Frfr5L33lHT6VrVpgiUdjxdWAIi-CkIV5Fzb-zksCCVXbqQUxqoSSmYCORp3BRchYEjmPsMj9KXiQnHpnZPadDaFC0IzpflUjvmMZSzD4BcKVK43trGVCJyoQR7WEKbz0hsjNZzCjlIDeKoBTyvAG6Su8ds8WUF3-cf1O7LXT-JhOnweDa7Ivh6qnPq4JrVisYIbsiu_is_l4tb8Bd8Bsa65
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Towards+Transparent+Deep+Learning%3A+Neural+Precoder+Design+for+Downlink+RSMA&rft.jtitle=IEEE+transactions+on+communications&rft.au=Wang%2C+Chao&rft.au=Li%2C+Guo&rft.au=Li%2C+Zan&rft.au=Zhang%2C+Haibin&rft.date=2025&rft.issn=0090-6778&rft.eissn=1558-0857&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FTCOMM.2025.3626023&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TCOMM_2025_3626023
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0090-6778&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0090-6778&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0090-6778&client=summon