Adaptive Retransmission Design for Wireless Federated Edge Learning

doi:10.12142/ZTECOM.202301002

ZTE Communications ›› 2023, Vol. 21 ›› Issue (1): 3-14.DOI: 10.12142/ZTECOM.202301002

• Special Topic • Previous Articles Next Articles

Adaptive Retransmission Design for Wireless Federated Edge Learning

XU Xinyi, LIU Shengli, YU Guanding()

Zhejiang University, Hangzhou 310027, China

Received:2022-10-27 Online:2023-03-25 Published:2023-03-22
About author:XU Xinyi received her BE degree in communication engineering from Zhejiang University, China in 2021. Now she is working towards her MS degree with the College of Information Science and Electronic Engineering, Zhejiang University. Her research interest focuses on federated learning.
LIU Shengli received his BS degree in information engineering from Soochow University, China in 2017, and his PhD degree from the College of Information Science and Electronic Engineering, Zhejiang University, China in 2022. He currently holds a post-doctoral position at the College of Information Science and Electronic Engineering, Zhejiang University. In 2021, he was a Visiting Research Scholar with the Centre for Wireless Communication, University of Oulu, Finland and the VTT Technical Research Centre of Finland. His current research interests mainly include machine learning and federated learning.
YU Guanding (yuguanding@zju.edu.cn) received his BE and PhD degrees in communication engineering from Zhejiang University, China in 2001 and 2006, respectively. He joined Zhejiang University in 2006 and is now a professor with the College of Information and Electronic Engineering. From 2013 to 2015, he was also a visiting professor at the School of Electrical and Computer Engineering, Georgia Institute of Technology, USA. His research interests include 5G communications and networks, mobile edge computing, and machine learning for wireless networks.

Abstract

Abstract:

As a popular distributed machine learning framework, wireless federated edge learning (FEEL) can keep original data local, while uploading model training updates to protect privacy and prevent data silos. However, since wireless channels are usually unreliable, there is no guarantee that the model updates uploaded by local devices are correct, thus greatly degrading the performance of the wireless FEEL. Conventional retransmission schemes designed for wireless systems generally aim to maximize the system throughput or minimize the packet error rate, which is not suitable for the FEEL system. A novel retransmission scheme is proposed for the FEEL system to make a tradeoff between model training accuracy and retransmission latency. In the proposed scheme, a retransmission device selection criterion is first designed based on the channel condition, the number of local data, and the importance of model updates. In addition, we design the air interface signaling under this retransmission scheme to facilitate the implementation of the proposed scheme in practical scenarios. Finally, the effectiveness of the proposed retransmission scheme is validated through simulation experiments.

Key words: federated edge learning, retransmission, unreliable communication, convergence rate, retransmission latency

XU Xinyi, LIU Shengli, YU Guanding. Adaptive Retransmission Design for Wireless Federated Edge Learning[J]. ZTE Communications, 2023, 21(1): 3-14.

Figures/Tables 6

Figure 1 Federated edge learning system

Table 1 Loss function for popular machine learning models

Learning Model	Loss Function $f (w, x, y)$
Linear regression	$12 y - w T x 2$
Least-squared support vector machine	$12 m a x {0,1 - y w T x} 2$
Neural network	$12 y - ϕ (w, x)$ , where $ϕ (w, x)$ is the learning output

Table 1 Loss function for popular machine learning models

Learning Model	Loss Function $f (w, x, y)$
Linear regression	$12 y - w T x 2$
Least-squared support vector machine	$12 m a x {0,1 - y w T x} 2$
Neural network	$12 y - ϕ (w, x)$ , where $ϕ (w, x)$ is the learning output

Figure 2 Retransmission signaling

Table 2 Simulation parameters

Parameters	Values
Path loss model	$128.1 + 37.6 l o g d$
Transmission power of the edge server	33 dBm
Transmission power of device	28 dBm
Additive white Gaussian noise power	-174 dBm/Hz
Bandwidth of downlink	10 MHz
Quantization bit of each element	16
Number of devices	10
Bandwidth of uplink	10 MHz
CRC code	32

Table 2 Simulation parameters

Parameters	Values
Path loss model	$128.1 + 37.6 l o g d$
Transmission power of the edge server	33 dBm
Transmission power of device	28 dBm
Additive white Gaussian noise power	-174 dBm/Hz
Bandwidth of downlink	10 MHz
Quantization bit of each element	16
Number of devices	10
Bandwidth of uplink	10 MHz
CRC code	32

Figure 3 Performance comparison between transmission schemes under CIFAR-10

Figure 4 Performance comparison between different retransmission schemes under CIFAR-10 with device number K=20

References 32

1	ZHANG T, GAO L, HE C Y, et al. Federated learning for the Internet of Things: applications, challenges, and opportunities [J]. IEEE Internet of Things magazine, 2022, 5(1): 24–29. DOI: 10.1109/IOTM.004.2100182
2	GUO F X, YU F R, ZHANG H L, et al. Enabling massive IoT toward 6G: a comprehensive survey [J]. IEEE Internet of Things journal, 2021, 8(15): 11891–11915. DOI: 10.1109/JIOT.2021.3063686
3	MOHAMMADI F G, SHENAVARMASOULEH F, ARABNIA H R. Applications of machine learning in healthcare and Internet of Things (IOT): a comprehensive review [EB/OL]. [2022-10-10].
4	VERBRAEKEN J, WOLTING M, KATZY J, et al. A survey on distributed machine learning [J]. ACM computing surveys, 2021, 53(2): 1–33. DOI: 10.1145/3377454
5	MAJEED I A, KAUSHIK S, BARDHAN A, et al. Comparative assessment of federated and centralized machine learning [EB/OL]. [2022-10-10].
6	GUPTA R, ALAM T. Survey on federated-learning approaches in distributed environment [J]. Wireless personal communications, 2022, 125(2): 1631–1652. DOI: 10.1007/s11277-022-09624-y
7	JIANG Y L, ZHANG K, QIAN Y, et al. Anonymous and efficient authentication scheme for privacy-preserving distributed learning [J]. IEEE transactions on information forensics and security, 2022, 17: 2227–2240. DOI: 10.1109/TIFS.2022.3181848
8	TRELEAVEN P, SMIETANKA M, PITHADIA H. Federated learning: the pioneering distributed machine learning and privacy-preserving data technology [J]. Computer, 2022, 55(4): 20–29. DOI: 10.1109/MC.2021.3052390
9	LI T, SAHU A K, TALWALKAR A, et al. Federated learning: challenges, methods, and future directions [J]. IEEE signal processing magazine, 2020, 37(3): 50–60. DOI: 10.1109/MSP.2020.2975749
10	LIU J, HUANG J Z, ZHOU Y, et al. From distributed machine learning to federated learning: A survey [J]. Knowledge and information systems, 2022, 64(4): 885–917. DOI: 10.1007/s10115-022-01664-x
11	ALEDHARI M, RAZZAK R, PARIZI R M, et al. Federated learning: a survey on enabling technologies, protocols, and applications [J]. IEEE access: practical innovations, open solutions, 2020, 8: 140699–140725. DOI: 10.1109/access.2020.3013541
12	ABREHA H G, HAYAJNEH M, SERHANI M A. Federated learning in edge computing: a systematic survey [J]. Sensor, 2022, 22(2): 450. DOI: 10.3390/s22020450
13	LIM W Y B, LUONG N C, HOANG D T, et al. Federated learning in mobile edge networks: a comprehensive survey [J]. IEEE communications surveys & tutorials, 2020, 22(3): 2031–2063. DOI: 10.1109/COMST.2020.2986024
14	NGUYEN D C, PHAM Q V, PATHIRANA P N, et al. Federated learning for smart healthcare: a survey [J]. ACM computing surveys, 2023, 55(3): 1–37. DOI: 10.1145/3501296
15	ZHENG Z H, ZHOU Y Z, SUN Y L, et al. Applications of federated learning in smart cities: Recent advances, taxonomy, and open challenges [J]. Connection science, 2022, 34(1): 1–28. DOI: 10.1080/09540091.2021.1936455
16	YANG Z H, CHEN M Z, SAAD W, et al. Energy efficient federated learning over wireless communication networks [J]. IEEE transactions on wireless communications, 2021, 20(3): 1935–1949. DOI: 10.1109/TWC.2020.3037554
17	CHEN M Z, YANG Z H, SAAD W, et al. A joint learning and communications framework for federated learning over wireless networks [J]. IEEE transactions on wireless communications, 2021, 20(1): 269–283. DOI: 10.1109/TWC.2020.3024629
18	NADEEM F, LI Y H, VUCETIC B, et al. Analysis and optimization of HARQ for URLLC [C]//IEEE Globecom Workshops. IEEE, 2022: 1–6. DOI: 10.1109/GCWkshps52748.2021.9682028
19	JIANG P W, WEN C K, JIN S, et al. Deep source-channel coding for sentence semantic transmission with HARQ [J]. IEEE transactions on communications, 2022, 70(8): 5225–5240. DOI: 10.1109/TCOMM.2022.3180997
20	SHIRVANIMOGHADDAM M, SALARI A, GAO Y F, et al. Federated learning with erroneous communication links [J]. IEEE communications letters, 2022, 26(6): 1293–1297. DOI: 10.1109/LCOMM.2022.3167094
21	SALARI A, SHIRVANIMOGHADDAM M, VUCETIC B, et al. Rate-convergence tradeoff of federated learning over wireless channel [EB/OL]. [2022-10-10].
22	YE H, LIANG L, LI G Y. Decentralized federated learning with unreliable communications [J]. IEEE journal of selected topics in signal processing, 2022, 16(3): 487–500. DOI: 10.1109/JSTSP.2022.3152445
23	JEONG E, ZECCHIN M, KOUNTOURIS M. Asynchronous decentralized learning over unreliable wireless networks [EB/OL]. [2022-10-10].
24	LI Z D, ZHOU Y J, WU D P, et al. Fairness-aware federated learning with unreliable links in resource-constrained Internet of Things [J]. IEEE Internet of Things journal, 2022, 9(18): 17359–17371. DOI: 10.1109/JIOT.2022.3156046
25	MAO Y Z, ZHAO Z H, YANG M L, et al. SAFARI: sparsity enabled federated learning with limited and unreliable communications [EB/OL]. [2022-10-10].
26	SALEHI M, HOSSAIN E. Federated learning in unreliable and resource-constrained cellular wireless networks [J]. IEEE transactions on communications, 2021, 69(8): 5136–5151. DOI: 10.1109/TCOMM.2021.3081746
27	JIANG Z H, YU G D, CAI Y L, et al. Decentralized edge learning via unreliable device-to-device communications [J]. IEEE transactions on wireless communications, 2022, 21(11): 9041–9055. DOI: 10.1109/TWC.2022.3172147
28	NADEEM F, LI Y H, VUCETIC B, et al. HARQ optimization for real-time remote estimation in wireless networked control [EB/OL]. [2022-10-10].
29	SHAH S W H, RAHMAN M M U, MIAN A N, et al. Effective capacity analysis of HARQ-enabled D2D communication in multi-tier cellular networks [J]. IEEE transactions on vehicular technology, 2021, 70(9): 9144–9159. DOI: 10.1109/TVT.2021.3100675
30	LIU D Z, ZHU G X, ZENG Q S, et al. Wireless data acquisition for edge learning: data-importance aware retransmission [J]. IEEE transactions on wireless communications, 2021, 20(1): 406–420. DOI: 10.1109/TWC.2020.3024980
31	SIMONSSON A, FURUSKAR A. Uplink power control in LTE - overview and performance, subtitle: principles and benefits of utilizing rather than compensating for SINR variations [C]//IEEE 68th Vehicular Technology Conference. IEEE, 2008: 1–5. DOI: 10.1109/VETECF.2008.317
32	XI Y, BURR A, WEI J B, et al. A general upper bound to evaluate packet error rate over quasi-static fading channels [J]. IEEE transactions on wireless communications, 2011, 10(5): 1373–1377. DOI: 10.1109/TWC.2011.012411.100787

[1]	JIANG Zhihui, HE Yinghui, YU Guanding. Joint User Selection and Resource Allocation for Fast Federated Edge Learning [J]. ZTE Communications, 2020, 18(2): 20-30.
[2]	HUANG He, LIU Yang, LIU Zhuang, HAN Jiren, GAO Yin. Mechanism of Fast Data Retransmission in CU-DU Split Architecture of 5G NR [J]. ZTE Communications, 2018, 16(3): 40-44.

Adaptive Retransmission Design for Wireless Federated Edge Learning

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 6

References 32

Related Articles 2

Recommended Articles

Metrics