Hierarchical Federated Learning: Architecture, Challenges, and Its Implementation in Vehicular Networks

doi:10.12142/ZTECOM.202301005

Abstract

Abstract:

Federated learning (FL) is a distributed machine learning (ML) framework where several clients cooperatively train an ML model by exchanging the model parameters without directly sharing their local data. In FL, the limited number of participants for model aggregation and communication latency are two major bottlenecks. Hierarchical federated learning (HFL), with a cloud-edge-client hierarchy, can leverage the large coverage of cloud servers and the low transmission latency of edge servers. There are growing research interests in implementing FL in vehicular networks due to the requirements of timely ML training for intelligent vehicles. However, the limited number of participants in vehicular networks and vehicle mobility degrade the performance of FL training. In this context, HFL, which stands out for lower latency, wider coverage and more participants, is promising in vehicular networks. In this paper, we begin with the background and motivation of HFL and the feasibility of implementing HFL in vehicular networks. Then, the architecture of HFL is illustrated. Next, we clarify new issues in HFL and review several existing solutions. Furthermore, we introduce some typical use cases in vehicular networks as well as our initial efforts on implementing HFL in vehicular networks. Finally, we conclude with future research directions.

Key words: hierarchical federated learning, vehicular network, mobility, convergence analysis

YAN Jintao, CHEN Tan, XIE Bowen, SUN Yuxuan, ZHOU Sheng, NIU Zhisheng. Hierarchical Federated Learning: Architecture, Challenges, and Its Implementation in Vehicular Networks[J]. ZTE Communications, 2023, 21(1): 38-45.

Figures/Tables 7

References 34

1	CHEN M Z, GÜNDÜZ D, HUANG K B, et al. Distributed learning in wireless networks: recent progress and future challenges [J]. IEEE journal on selected areas in communications, 2021, 39(12): 3579–3605. DOI: 10.1109/JSAC.2021.3118346
2	SUN Y X, SHI W Q, HUANG X F, et al. Edge learning with timeliness constraints: challenges and solutions [J]. IEEE communications magazine, 2020, 58(12): 27–33. DOI: 10.1109/MCOM.001.2000382
3	SHI Y M, YANG K, JIANG T, et al. Communication-efficient edge AI: algorithms and systems [J]. IEEE communications surveys & tutorials, 2020, 22(4): 2167–2191. DOI: 10.1109/comst.2020.3007787
4	ABAD M S H, OZFATURA E, GUNDUZ D, et al. Hierarchical federated learning across heterogeneous cellular networks [C]//IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020: 8866–8870. DOI: 10.1109/ICASSP40776.2020.9054634
5	LIU L M, ZHANG J, SONG S H, et al. Client-edge-cloud hierarchical federated learning [C]//IEEE International Conference on Communications (ICC). IEEE, 2020: 1–6. DOI: 10.1109/ICC40277.2020.9148862
6	SUN Y X, XIE B W, ZHOU S, et al. MEET: mobility-enhanced edge intelligence for smart and green 6G networks [J]. IEEE communications magazine, 2023, 61(1): 64–70. DOI: 10.1109/MCOM.001.2200252
7	SAMARAKOON S, BENNIS M, SAAD W, et al. Distributed federated learning for ultra-reliable low-latency vehicular communications [J]. IEEE transactions on communications, 2020, 68(2): 1146–1159. DOI: 10.1109/TCOMM.2019.2956472
8	YU Z X, HU J, MIN G Y, et al. Mobility-aware proactive edge caching for connected vehicles using federated learning [J]. IEEE transactions on intelligent transportation systems, 2021, 22(8): 5341–5351. DOI: 10.1109/TITS.2020.3017474
9	XIAO H Z, ZHAO J, PEI Q Q, et al. Vehicle selection and resource optimization for federated learning in vehicular edge computing [J]. IEEE transactions on intelligent transportation systems, 2022, 23(8): 11073–11087. DOI: 10.1109/TITS.2021.3099597
10	WANG S Y, LIU F F, XIA H L. Content-based vehicle selection and resource allocation for federated learning in IoV [C]//IEEE Wireless Communications and Networking Conference Workshops (WCNCW). IEEE, 2021: 1–7. DOI: 10.1109/WCNCW49093.2021.9419986
11	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
12	ELBIR A M, SONER B, ÇÖLERI S, et al. Federated learning in vehicular networks [C]//IEEE International Mediterranean Conference on Communications and Networking (MeditCom). IEEE, 2022: 72–77. DOI: 10.1109/MeditCom55741.2022.9928621
13	LIU L M, ZHANG J, SONG S H, et al. Hierarchical federated learning with quantization: convergence analysis and system design [J]. IEEE transactions on wireless communications, 2023, 22(1): 2–18. DOI: 10.1109/TWC.2022.3190512
14	CASTIGLIA T, DAS A, PATTERSON S. Multi-level local SGD: distributed SGD for heterogeneous hierarchical networks [C/OL]. International Conference on Learning Representations, 2021 [2021-05-03].
15	WANG J Y, WANG S Q, CHEN R R, et al. Demystifying why local aggregation helps: convergence analysis of hierarchical SGD [J]. Proceedings of the AAAI conference on artificial intelligence, 2022, 36(8): 8548–8556. DOI: 10.1609/aaai.v36i8.20832
16	FENG C, YANG H H, HU D, et al. Mobility-aware cluster federated learning in hierarchical wireless networks [J]. IEEE transactions on wireless communications, 2022, 21(10): 8441–8458. DOI: 10.1109/TWC.2022.3166386
17	LUO S Q, CHEN X, WU Q, et al. HFEL: joint edge association and resource allocation for cost-efficient hierarchical federated edge learning [J]. IEEE transactions on wireless communications, 2020, 19(10): 6535–6548. DOI: 10.1109/TWC.2020.3003744
18	LIM W Y B, NG J S, XIONG Z H, et al. Dynamic edge association and resource allocation in self-organizing hierarchical federated learning networks [J]. IEEE journal on selected areas in communications, 2021, 39(12): 3640–3653. DOI: 10.1109/JSAC.2021.3118401
19	LIU S L, YU G D, CHEN X F, et al. Joint user association and resource allocation for wireless hierarchical federated learning with non-IID data [C]//IEEE International Conference on Communications. IEEE, 2022: 74–79. DOI: 10.1109/ICC45855.2022.9839164
20	XU B, XIA W C, WEN W L, et al. Adaptive hierarchical federated learning over wireless networks [J]. IEEE transactions on vehicular technology, 2022, 71(2): 2070–2083. DOI: 10.1109/tvt.2021.3135541
21	LIM W Y B, NG J S, XIONG Z H, et al. Decentralized edge intelligence: a dynamic resource allocation framework for hierarchical federated learning [J]. IEEE transactions on parallel and distributed systems, 2022, 33(3): 536–550. DOI: 10.1109/TPDS.2021.3096076
22	HOSSEINALIPOUR S, AZAM S S, BRINTON C G, et al. Multi-stage hybrid federated learning over large-scale D2D-enabled fog networks [J]. IEEE/ACM transactions on networking, 2022, 30(4): 1569–1584. DOI: 10.1109/TNET.2022.3143495
23	DU Z Y, WU C, YOSHINAGA T, et al. Federated learning for vehicular Internet of Things: recent advances and open issues [J]. IEEE open journal of the computer society, 2020, 1: 45–61. DOI: 10.1109/OJCS.2020.2992630
24	MA Y X, ZHU X G, ZHANG S B, et al. TrafficPredict: trajectory prediction for heterogeneous traffic-agents [J]. Proceedings of the AAAI conference on artificial intelligence. AAAI, 2019, 33(1): 6120–6127. DOI: 10.1609/aaai.v33i01.33016120
25	ALTCHÉ F, DE LA FORTELLE A. An LSTM network for highway trajectory prediction [C]//IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2018: 353–359. DOI: 10.1109/ITSC.2017.8317913
26	SHALEV-SHWARTZ S, SHAMMAH S, Safe SHASHUA A., multi-agent, reinforcement learning for autonomous driving [EB/OL]. (2016-10-11)[2022-05-01].
27	QURESHI K N, ABDULLAH A H. A survey on intelligent transportation systems [J]. Middle-east journal of scientific research, 2013, 15(5): 629–642. DOI: 10.5829/idosi.mejsr.2013.15.5.11215
28	MAO R, GUO J, JIA Y, et al. DOLPHINS: dataset for collaborative perception enabled harmonious and interconnected self-driving [EB/OL]. (2022-07-15)[2022-08-01].
29	AXELSSON J. Safety in vehicle platooning: a systematic literature review [J]. IEEE transactions on intelligent transportation systems, 2017, 18(5): 1033–1045. DOI: 10.1109/TITS.2016.2598873
30	PRATHIBA S B, RAJA G, DEV K, et al. A hybrid deep reinforcement learning for autonomous vehicles smart-platooning [J]. IEEE transactions on vehicular technology, 2021, 70(12): 13340–13350. DOI: 10.1109/TVT.2021.3122257
31	KLAUTAU A, BATISTA P, GONZÁLEZ-PRELCIC N, et al. 5G MIMO data for machine learning: application to beam-selection using deep learning [C]//Information Theory and Applications Workshop (ITA). IEEE, 2018: 1–9. DOI: 10.1109/ITA.2018.8503086
32	ALDOSSARI S M, CHEN K C. Machine learning for wireless communication channel modeling: an overview [J]. Wireless personal communications, 2019, 106(1): 41–70. DOI: 10.1007/s11277-019-06275-4
33	KURKA D B, GÜNDÜZ D. Bandwidth-agile image transmission with deep joint source-channel coding [J]. IEEE transactions on wireless communications, 2021, 20(12): 8081–8095. DOI: 10.1109/TWC.2021.3090048
34	KRIZHEVSKY A. Learning multiple layers of features from tiny images [D]. Toronto: University of Toronto, 2009

Highlight	Reference
A comprehensive survey of FL in wireless networks	Ref. [1]
A tutorial on timely edge learning, aiming to minimize the communication and computation latency in FL training	Ref. [2]
A comprehensive survey of FL and MEC	Ref. [11]
A tutorial on the implementation of FL in vehicular networks and the major challenges of learning and communications	Ref. [12]

Highlight	Reference
A comprehensive survey of FL in wireless networks	Ref. [1]
A tutorial on timely edge learning, aiming to minimize the communication and computation latency in FL training	Ref. [2]
A comprehensive survey of FL and MEC	Ref. [11]
A tutorial on the implementation of FL in vehicular networks and the major challenges of learning and communications	Ref. [12]

Category	Highlight	Reference
Convergence analysis	Effect of edge and cloud aggregation intervals and local update step size with both convex and non-convex loss functions	Ref. [5]
	Extending Ref. [5] into HFL with quantization and carrying out the convergence analysis	Ref. [13]
	Effect of local iterations, edge epochs, global epochs, network topology and node heterogeneity on the convergence performance for a graph-based edge topology	Ref. [14]
	Extending Ref. [14] into HFL with data heterogeneity, random grouping and multi-layer architecture	Ref. [15]
	Mobility-aware HFL	Ref. [16]
Resource management	Joint resource allocation and edge association	Refs. [17–19]
	Joint resource allocation and interval control	Ref. [20]
	Joint resource allocation and incentive mechanism design	Ref. [21]
Other practical considerations	Multi-stage HFL with device-to-device communications	Ref. [22]

Category	Highlight	Reference
Convergence analysis	Effect of edge and cloud aggregation intervals and local update step size with both convex and non-convex loss functions	Ref. [5]
	Extending Ref. [5] into HFL with quantization and carrying out the convergence analysis	Ref. [13]
	Effect of local iterations, edge epochs, global epochs, network topology and node heterogeneity on the convergence performance for a graph-based edge topology	Ref. [14]
	Extending Ref. [14] into HFL with data heterogeneity, random grouping and multi-layer architecture	Ref. [15]
	Mobility-aware HFL	Ref. [16]
Resource management	Joint resource allocation and edge association	Refs. [17–19]
	Joint resource allocation and interval control	Ref. [20]
	Joint resource allocation and incentive mechanism design	Ref. [21]
Other practical considerations	Multi-stage HFL with device-to-device communications	Ref. [22]

[1]	GU Cheng, LI Baochun. Hierarchical Federated Learning Architectures for the Metaverse [J]. ZTE Communications, 2024, 22(2): 39-48.
[2]	ZHANG Zhengquan, LIU Heng, WANG Qianli, FAN Pingzhi. A Survey on Low Complexity Detectors for OTFS Systems [J]. ZTE Communications, 2021, 19(4): 3-15.
[3]	ZHANG Man, LI Dapeng, LIU Zhuang, GAO Yin. QoE Management for 5G New Radio [J]. ZTE Communications, 2021, 19(3): 64-72.
[4]	YANG Haojun, ZHENG Kan, LEI Lei, and XIANG Wei. Heterogeneous Vehicular Networks for Social Networks: Requirements and Challenges [J]. ZTE Communications, 2016, 14(3): 29-35.
[5]	Smitha Shivshankar and Abbas Jamalipour. A Cloud Computing Perspective for Distributed Routing in Vehicular Environments [J]. ZTE Communications, 2016, 14(3): 36-44.
[6]	Somayya Madakam, Ramaswamy Ramachandran. Barcelona Smart City: The Heaven on Earth (Internet of Things: Technological God) [J]. ZTE Communications, 2015, 13(4): 3-9.
[7]	Jiannong Cao. Vehicular Networks [J]. ZTE Communications, 2014, 12(1): 1-2.
[8]	Florian Hagenauer, Patrick Baldemaier, Falko Dressler, Christoph Sommer. Advanced Leader Election for Virtual Traffic Lights [J]. ZTE Communications, 2014, 12(1): 11-16.
[9]	Jaehoon (Paul) Jeong, Tian He, David H.C.Du. Trajectory-Based Data Forwarding Schemes for Vehicular Networks [J]. ZTE Communications, 2014, 12(1): 17-25.
[10]	Zhenni Feng, Yanmin Zhu, Qian Zhang, Min Gao. Unveiling the Challenges in Improving Data Availability in Vehicular Networks with Network Coding [J]. ZTE Communications, 2014, 12(1): 26-32.
[11]	Yi Zhu and Zhengkun Mi. Content Centric Networking: A New Approach to Big Data Distribution [J]. ZTE Communications, 2013, 11(2): 3-10.
[12]	Yuhong Li, Yunjing Hou, and Shiduan Cheng. A Mobility Management Solution Based on ID/Locator Separation [J]. ZTE Communications, 2011, 9(2): 39-43.
[13]	Liu Fuqiang, Shan Lianhai. Heterogeneous Vehicular Communication Architecture and Key Technologies [J]. ZTE Communications, 2010, 8(4): 39-44.