CoChat

Machine Learning for Large-Scale Optimization in 6G Wireless Networks

Open access
Shi, Yandong, Lian, Lixiang, Shi, Yuanming, Wang, Zixin, Zhou, Yong, Fu, Liqun, Bai, Lin, Zhang, Jun, Zhang, Wei · 2023 · IEEE Communications Surveys & Tutorials
Cited by 205

The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.

Abstract

The sixth generation (6G) wireless systems are envisioned to enable the paradigm shift from “connected things” to “connected intelligence”, featured by ultra high density, large-scale, dynamic heterogeneity, diversified functional requirements, and machine learning capabilities, which leads to a growing need for highly efficient intelligent algorithms. The classic optimization-based algorithms usually require highly precise mathematical model of data links and suffer from poor performance with high computational cost in realistic 6G applications. Based on domain knowledge (e.g., optimization models and theoretical tools), machine learning (ML) stands out as a promising and viable methodology for many complex large-scale optimization problems in 6G, due to its superior performance, computational efficiency, scalability, and generalizability. In this paper, we systematically review the most representative “learning to optimize" techniques in diverse domains of 6G wireless networks by identifying the inherent feature of the underlying optimization problem and investigating the specifically designed ML frameworks from the perspective of optimization. In particular, we will cover algorithm unrolling, learning to branch-and-bound, graph neural network for structured optimization, deep reinforcement learning for stochastic optimization, end-to-end learning for semantic optimization, as well as wireless federated learning for distributed optimization, which are capable of addressing challenging large-scale problems arising from a variety of crucial wireless applications. Through the in-depth discussion, we shed light on the excellent performance of ML-based optimization algorithms with respect to the classical methods, and provide insightful guidance to develop advanced ML techniques in 6G networks. Neural network design, theoretical tools of different ML methods, implementation issues, as well as challenges and future research directions are also discussed to support the practical use of the ML model in 6G wireless networks.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/comst.2023.3300664

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 241

  1. 10.1109/COMST.2021.3131332 · DOI · Paper page
  2. 10.1109/COMST.2021.3130901 · DOI · Paper page
  3. 10.1109/MCOM.2019.1900271 · DOI · Paper page
  4. 2022, 6G vision and candidate technologies
  5. 10.1109/jsac.2023.3280978 · DOI
  6. 10.1109/JPROC.2021.3061701 · DOI · Paper page
  7. 10.1109/MSP.2014.2377273 · DOI · Paper page
  8. 10.1109/MWC.2015.7143330 · DOI · Paper page
  9. 10.1109/MNET.121.2100320 · DOI
  10. Beck, 2022, Semantic communication: An information bottleneck view, arXiv:2204.13366 · arXiv
  11. 10.1109/twc.2023.3284263 · DOI
  12. 10.1109/ISIT.2015.7282651 · DOI · Paper page
  13. 10.1109/TIT.2007.909108 · DOI · Paper page
  14. 10.1109/TWC.2020.2996144 · DOI
  15. 10.1109/TWC.2021.3120926 · DOI
  16. 10.1109/TIT.2008.917634 · DOI
  17. 10.1109/TSP.2017.2690386 · DOI
  18. 10.1109/TCOMM.2021.3114791 · DOI · Paper page
  19. 10.1109/MBITS.2022.3212978 · DOI
  20. 10.1109/JSAC.2021.3078500 · DOI
  21. 10.1109/TWC.2021.3100500 · DOI
  22. 10.1109/COMST.2022.3156207 · DOI
  23. Amos, 2022, Tutorial on amortized optimization for learning to optimize over continuous domains, arXiv:2202.00665 · arXiv
  24. 10.1109/ACCESS.2022.3218802 · DOI · Paper page
  25. 10.1109/TWC.2022.3219840 · DOI · Paper page
  26. 10.1109/TCOMM.2019.2924010 · DOI · Paper page
  27. 10.1109/TSP.2020.2976585 · DOI · Paper page
  28. 10.1109/TCOMM.2020.3027027 · DOI · Paper page
  29. 10.1109/TWC.2022.3181219 · DOI
  30. Khan, 2018, Scalable centralized deep multi-agent reinforcement learning via policy gradients, arXiv:1805.08776 · arXiv
  31. 10.1109/MWC.006.2100543 · DOI · Paper page
  32. 10.1109/TSP.2022.3143372 · DOI
  33. 10.1109/TWC.2020.3030882 · DOI
  34. 10.1109/TCOMM.2021.3135540 · DOI
  35. 10.1109/MCOM.001.2001239 · DOI · Paper page
  36. 10.1109/MCOM.101.2100138 · DOI
  37. 10.1109/LCOMM.2019.2898944 · DOI · Paper page
  38. Haykin, 2004, A comprehensive foundation, Neural Netw., 2, 41
  39. 10.1109/TVT.2019.2897134 · DOI · Paper page
  40. 10.1109/MSP.2020.3016905 · DOI · Paper page
  41. 10.1109/OJCOMS.2022.3210648 · DOI
  42. 10.1109/COMST.2019.2904897 · DOI · Paper page
  43. 10.1109/COMST.2019.2926625 · DOI · Paper page
  44. 10.1109/JSAC.2019.2933969 · DOI · Paper page
  45. 10.1109/MWC.001.2200023 · DOI
  46. 10.1109/COMST.2022.3223224 · DOI · Paper page
  47. 10.1109/COMST.2019.2916583 · DOI · Paper page
  48. 10.1109/COMST.2021.3089688 · DOI · Paper page
  49. 10.1109/COMST.2022.3199544 · DOI · Paper page
  50. 10.1109/COMST.2020.2988367 · DOI · Paper page
  51. 10.1109/TSP.2021.3079807 · DOI
  52. 10.1109/TWC.2021.3123620 · DOI
  53. 10.1109/JSAC.2021.3078502 · DOI · Paper page
  54. 10.1109/TWC.2020.3040983 · DOI · Paper page
  55. 10.1109/TSP.2022.3163626 · DOI
  56. 10.1109/TITS.2019.2963722 · DOI · Paper page
  57. 10.1109/LCOMM.2020.2990487 · DOI
  58. 10.1109/APCC.2018.8633520 · DOI
  59. 10.1109/ICC.2017.7997286 · DOI · Paper page
  60. 10.1109/ACCESS.2019.2959348 · DOI
  61. 10.1109/JIOT.2021.3058236 · DOI
  62. 10.1109/JSAC.2022.3221990 · DOI · Paper page
  63. 10.1109/JSAC.2022.3221977 · DOI · Paper page
  64. 10.1109/JSAC.2021.3087240 · DOI · Paper page
  65. 10.1109/jsac.2022.3221991 · DOI · Paper page
  66. 10.1109/LCOMM.2020.3019312 · DOI
  67. 10.1109/TWC.2021.3128392 · DOI · Paper page
  68. 10.1109/INFOCOM41043.2020.9155494 · DOI · Paper page
  69. 10.1109/ICC45855.2022.9838703 · DOI
  70. Gregor, Learning fast approximations of sparse coding, 399
  71. 10.1109/TSP.2017.2708040 · DOI · Paper page
  72. Chen, 2021, Learning to optimize: A primer and a benchmark, arXiv:2103.12828 · arXiv
  73. 10.1109/TPAMI.2018.2883941 · DOI · Paper page
  74. 10.1109/ICASSP.2019.8682542 · DOI
  75. 10.1109/TCOMM.2021.3114682 · DOI
  76. 10.1109/TWC.2022.3142737 · DOI
  77. 10.1109/JIOT.2021.3097133 · DOI
  78. 10.1109/TWC.2021.3072382 · DOI
  79. 10.1109/TWC.2022.3166964 · DOI
  80. 10.1561/2000000093 · DOI · Paper page
  81. 10.1109/18.771234 · DOI
  82. 10.1109/TCI.2020.2964202 · DOI · Paper page
  83. 10.2307/1910129 · DOI · Paper page
  84. Huang, 2021, Branch and bound in mixed integer linear programming problems: A survey of techniques and trends, arXiv:2111.06257 · arXiv
  85. 10.1287/ijoc.2016.0723 · DOI · Paper page
  86. 10.1016/j.disopt.2016.01.005 · DOI · Paper page
  87. Gasse, Exact combinatorial optimization with graph convolutional neural networks, 15554
  88. Nair, 2020, Solving mixed integer programs using neural networks, arXiv:2012.13349 · arXiv
  89. He, Learning to search in branch and bound algorithms, 27, 3293
  90. 10.3390/ai2020010 · DOI
  91. 10.1109/49.793310 · DOI · Paper page
  92. 10.1109/TWC.2013.040413.120676 · DOI · Paper page
  93. 10.1109/TVT.2019.2953724 · DOI
  94. 10.2307/353415 · DOI · Paper page
  95. 10.1007/s10851-007-0008-7 · doi:10.1007/s10851-007-0008-7
  96. 10.1109/IJCNN.2010.5596450 · DOI
  97. 10.1109/LCOMM.2022.3159742 · DOI
  98. 10.1109/TSP.2017.2699640 · DOI
  99. 10.1109/mnet.123.2100773 · DOI
  100. 10.1109/GCWkshps45667.2019.9024538 · DOI · Paper page
  101. 10.1109/TWC.2022.3193138 · DOI
  102. 10.1109/ICASSP39728.2021.9414098 · DOI
  103. 10.1109/ICASSP43922.2022.9746926 · doi:10.1109/icassp43922.2022.9746926
  104. 10.1109/TSP.2023.3255547 · DOI
  105. 10.1109/TMC.2021.3125793 · DOI
  106. 10.1109/TWC.2021.3100133 · DOI
  107. 10.1109/TMC.2020.3020582 · DOI
  108. 10.1109/TMC.2021.3079117 · DOI
  109. 10.1109/GLOBECOM46510.2021.9685457 · DOI
  110. Garg, Generalization and representational limits of graph neural networks, 3419
  111. Alon, On the bottleneck of graph neural networks and its practical implications, 1
  112. Bertsekas, 1995, Dynamic Programming and Optimal Control
  113. 10.1109/TITS.2019.2906260 · DOI
  114. 10.1145/3219819.3220096 · DOI · Paper page
  115. 10.1109/WCNC49053.2021.9417262 · DOI
  116. 10.1109/ITSC.2018.8569568 · DOI · Paper page
  117. 10.1109/ITSC.2017.8317839 · DOI · Paper page
  118. 10.1016/j.trc.2019.08.011 · DOI · Paper page
  119. 10.1016/j.energy.2021.122523 · DOI
  120. 10.1109/VPPC.2018.8605023 · DOI
  121. 10.1109/ACCESS.2020.2991057 · DOI
  122. 10.1109/JIOT.2019.2928837 · DOI
  123. 10.1109/LWC.2021.3052079 · DOI
  124. 10.1145/3132847.3133045 · DOI
  125. 10.1109/MICRO50266.2020.00090 · DOI · Paper page
  126. 10.1145/3288599.3288634 · DOI
  127. 10.1109/TGCN.2020.3045075 · DOI
  128. 10.1109/CSCloud-EdgeCom52276.2021.00044 · DOI
  129. 10.1109/LCOMM.2020.3001227 · DOI
  130. 10.1109/LCOMM.2021.3053612 · DOI
  131. 10.1109/TWC.2020.2993071 · DOI · Paper page
  132. 10.1109/TPDS.2021.3132422 · DOI
  133. 10.1109/TNSE.2021.3068340 · DOI · Paper page
  134. 10.1109/TITS.2021.3128209 · DOI
  135. 10.1109/TII.2022.3164395 · DOI
  136. 10.1109/MWC.001.00254 · DOI
  137. 10.1109/JSTSP.2021.3135751 · DOI
  138. 10.1109/TWC.2020.3001736 · DOI · Paper page
  139. 10.1109/TITS.2021.3054511 · DOI
  140. 10.1016/j.jet.2004.03.008 · DOI · Paper page
  141. Littman, A generalized reinforcement-learning model: Convergence and applications, 96, 310
  142. Silver, Deterministic policy gradient algorithms, 387
  143. 10.1109/JSYST.2019.2933536 · DOI
  144. 10.1145/3466752.3480129 · DOI
  145. 10.1145/584091.584093 · DOI
  146. 10.1002/j.1538-7305.1948.tb01338.x · DOI · Paper page
  147. 10.1109/MWC.101.2100269 · DOI · Paper page
  148. 10.1017/9781108779302 · doi:10.1017/9781108779302
  149. Chechik, 2005, Information bottleneck for Gaussian variables, J. Mach. Learn. Res., 6, 165
  150. 10.1109/JSAIT.2020.2991561 · DOI · Paper page
  151. Alemi, Deep variational information bottleneck, 1
  152. Kingma, Auto-encoding variational Bayes, 1
  153. 10.1109/TCCN.2022.3173056 · DOI
  154. 10.1109/TCCN.2019.2919300 · DOI · Paper page
  155. 10.1109/JSAIT.2020.2987203 · DOI · Paper page
  156. 10.1109/JSAC.2022.3221968 · DOI · Paper page
  157. 10.1109/ICCWorkshops53468.2022.9814492 · DOI
  158. 10.1109/JSAC.2022.3191326 · DOI · Paper page
  159. 10.1109/TCSVT.2021.3082521 · DOI · Paper page
  160. 10.1109/JSAC.2022.3221999 · DOI · Paper page
  161. 10.1109/twc.2023.3240969 · DOI · Paper page
  162. 10.1109/JSAC.2022.3180802 · DOI · Paper page
  163. 10.1109/MWC.008.2200180 · DOI
  164. 10.1109/MCOM.001.2000604 · DOI · Paper page
  165. 10.1109/COMST.2021.3058573 · DOI · Paper page
  166. 10.1109/JIOT.2022.3168066 · DOI
  167. 10.1109/JSAC.2022.3180799 · DOI
  168. 10.1109/TNSE.2022.3178970 · DOI · Paper page
  169. 10.1109/TCOMM.2019.2944169 · DOI · Paper page
  170. 10.1109/TWC.2021.3062708 · DOI · Paper page
  171. 10.1109/TWC.2019.2946245 · DOI · Paper page
  172. Wang, 2022, Over-the-air computation: Foundations, technologies, and applications, arXiv:2210.10524 · arXiv
  173. 10.1109/TSP.2022.3171065 · doi:10.1109/tsp.2022.3171065
  174. 10.1109/TWC.2022.3227636 · DOI
  175. 10.1109/TII.2021.3064351 · DOI · Paper page
  176. 10.1109/JIOT.2020.3026589 · DOI · Paper page
  177. 10.1109/JIOT.2022.3174469 · DOI
  178. 10.1109/TCOMM.2020.3004524 · DOI
  179. 10.1109/TVT.2021.3131534 · DOI
  180. 10.1109/ACCESS.2021.3095915 · DOI
  181. 10.1109/VTC2021-Spring51267.2021.9448736 · DOI
  182. 10.1109/ICC42927.2021.9500603 · DOI
  183. 10.1109/GLOBECOM42002.2020.9348225 · DOI
  184. 10.1109/LNET.2022.3173971 · DOI
  185. Liu, A communication efficient vertical federated learning framework, 118
  186. 10.1137/1.9781611972726.18 · doi:10.1137/1.9781611972726.18
  187. 10.1109/MCOM.001.2001016 · DOI
  188. 10.1109/msp.2023.3262366 · doi:10.1109/msp.2023.3262366
  189. 10.1109/TVT.2019.2951501 · DOI · Paper page
  190. 10.1109/MNET.2019.1900029 · DOI
  191. 10.1109/LCOMM.2020.3035326 · DOI
  192. 10.1109/TSP.2019.2908906 · DOI · Paper page
  193. 10.1109/TWC.2020.2992786 · DOI
  194. 10.1109/ICC.2019.8761681 · DOI
  195. 10.1109/JSAC.2020.3036947 · DOI
  196. 10.1109/tnnls.2023.3283523 · DOI · Paper page
  197. You, Graph contrastive learning with augmentations, 33, 5812
  198. Zhu, Deep graph contrastive representation learning, 1
  199. Kingma, Adam: A method for stochastic optimization, 1
  200. 10.1109/TCCN.2021.3084409 · DOI

200 of 241 shown

Cited by

See all 205

Metadata

Authors
Shi, Y., Lian, L., Shi, Y., Wang, Z., Zhou, Y., Fu, L., Bai, L., Zhang, J., & Zhang, W.
Venue
IEEE Communications Surveys & Tutorials
Published
2023
Volume
25
Issue
4
Pages
2088-2132
ISSN
  • 1553-877X (ISSN-L)
  • 2373-745X
OpenAlex
W4385453555
Cited by
205
References
49
FWCI
15.03
Type
journal article
Language
en
Open access
green
Funders
  • National Nature Science Foundation of China (62101331, 62271318)
  • Natural Science Foundation of Shanghai (21ZR1442700, 23ZR1442800)
  • Shanghai Rising-Star Program (22QA1406100)
  • National Natural Science Foundation of China (U20A20159, 62001294)
  • Research Impact Fund (RIF) from Hong Kong RGC (R5009-21)
  • Special Project for Research and Development in Key areas of Guangdong Province (2020B0101110003)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.