Device Scheduling in Over-the-Air Federated Learning Via Matching Pursuit

被引：7

作者：

Bereyhi, Ali ^{[1
]}

Vagollari, Adela ^{[2
]}

Asaad, Saba ^{[3
]}

Muller, Ralf R. ^{[2
]}

Gerstacker, Wolfgang ^{[2
]}

Poor, H. Vincent ^{[4
]}

机构：

[1] Univ Toronto, Wireless Comp Lab, Toronto, ON M5S 2E4, Canada

[2] Friedrich Alexander Univ Erlangen Nurnberg, Inst Digital Commun, D-91058 Erlangen, Bayern, Germany

[3] York Univ, Next Generat Wireless Networks, Res Lab, Toronto, ON M3J 1P3, Canada

[4] Princeton Univ, Dept Elect & Comp Engn, Princeton, NJ 08544 USA

来源：

IEEE TRANSACTIONS ON SIGNAL PROCESSING | 2023年 / 71卷

基金：

美国国家科学基金会;

关键词：

Device scheduling; federated learning; matching pursuit; over-the-air computation; ANALOG FUNCTION COMPUTATION; ULTRA-DENSE NETWORKS; SIGNAL RECOVERY; ENABLING TECHNOLOGIES; ENERGY; ALGORITHMS; CHALLENGES;

D O I：

10.1109/TSP.2023.3284376

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper develops a class of low-complexity device scheduling algorithms for over-the-air federated learning via the method of matching pursuit. The proposed scheme tracks closely the close-to-optimal performance achieved by difference-of-convex programming, and outperforms significantly the well-known benchmark algorithms based on convex relaxation. Compared to the state-of-the-art, the proposed scheme imposes a drastically lower computational load on the system: for K devices and N antennas at the parameter server, the benchmark complexity scales with (N-2 + K)(3) + N-6 while the complexity of the proposed scheme scales with (KNq)-N-p for some 0 < p, q <= 2. The efficiency of the proposed scheme is confirmed through the convergence analysis and numerical experiments on CIFAR-10 dataset.

引用

页码：2188 / 2203

页数：16

共 50 条

[1] Device Scheduling for Over-the-Air Federated Learning with Differential Privacy
Yan, Na
Wang, Kezhi
Pan, Cunhua
Chai, Kok Keong
ICC 2023-IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, 2023, : 51 - 56
[2] Communication-Efficient Device Scheduling via Over-the-Air Computation for Federated Learning
Jiang, Bingqing
Du, Jun
Jiang, Chunxiao
Shi, Yuanming
Han, Zhu
2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 173 - 178
[3] Device Scheduling for Relay-Assisted Over-the-Air Aggregation in Federated Learning
Zhang, Fan
Chen, Jining
Wang, Kunlun
Chen, Wen
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2024, 73 (05) : 7412 - 7417
[4] Federated Learning via Over-the-Air Computation
Yang, Kai
Jiang, Tao
Shi, Yuanming
Ding, Zhi
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2020, 19 (03) : 2022 - 2035
[5] Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning
Sun, Yuchang
Lin, Zehong
Mao, Yuyi
Jin, Shi
Zhang, Jun
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2024, 23 (07) : 6905 - 6920
[6] Towards Differentially Private Over-the-Air Federated Learning via Device Sampling
Hu, Zihao
Yan, Jia
Zhang, Ying-Jun Angela
IEEE CONFERENCE ON GLOBAL COMMUNICATIONS, GLOBECOM, 2023, : 5292 - 5298
[7] User Scheduling for Federated Learning Through Over-the-Air Computation
Ma, Xiang
Sun, Haijian
Wang, Qun
Hu, Rose Qingyang
2021 IEEE 94TH VEHICULAR TECHNOLOGY CONFERENCE (VTC2021-FALL), 2021,
[8] Over-the-Air Federated Learning via Weighted Aggregation
Azimi-Abarghouyi, Seyed Mohammad
Tassiulas, Leandros
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2024, 23 (12) : 18240 - 18253
[9] Asynchronous Federated Learning via Over-the-air Computation
Zheng, Zijian
Deng, Yansha
Liu, Xiaonan
Nallanathan, Arumugam
IEEE CONFERENCE ON GLOBAL COMMUNICATIONS, GLOBECOM, 2023, : 1345 - 1350
[10] ROBUST FEDERATED LEARNING VIA OVER-THE-AIR COMPUTATION
Sifaou, Houssem
Li, Geoffrey Ye
2022 IEEE 32ND INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2022,

← 1 2 3 4 5 →