Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues

被引:16
作者
Akrout, Mohamed [1 ]
Feriani, Amal [1 ]
Bellili, Faouzi [1 ]
Mezghani, Amine [1 ]
Hossain, Ekram [1 ]
机构
[1] Univ Manitoba, Dept Elect & Comp Engn, Winnipeg, MB R2M 2J8, Canada
来源
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS | 2023年 / 25卷 / 04期
基金
加拿大自然科学与工程研究理事会;
关键词
ML-aided wireless networks; out-of-distribution generalization; domain generalization; CHANNEL ESTIMATION; DEEP; MIMO; DESIGN; NETWORKS; PHASE;
D O I
10.1109/COMST.2023.3326399
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Data-driven machine learning (ML) is promoted as one potential technology to be used in next-generation wireless systems. This led to a large body of research work that applies ML techniques to solve problems in different layers of the wireless transmission link. However, most of these applications rely on supervised learning which assumes that the source (training) and target (test) data are independent and identically distributed (i.i.d). This assumption is often violated in the real world due to domain or distribution shifts between the source and the target data. Thus, it is important to ensure that these algorithms generalize to out-of-distribution (OOD) data. In this context, domain generalization (DG) tackles the OOD-related issues by learning models on different and distinct source domains/datasets with generalization capabilities to unseen new domains without additional finetuning. Motivated by the importance of DG requirements for wireless applications, we present a comprehensive overview of the recent developments in DG and the different sources of domain shift. We also summarize the existing DG methods and review their applications in selected wireless communication problems, and conclude with insights and open questions.
引用
收藏
页码:3014 / 3037
页数:24
相关论文
共 26 条
[21]   An Investigation into the Performances of the State-of-the-art Machine Learning Approaches for Various Cyber-attack Detection: A Survey [J].
Ige, Tosin ;
Kiekintveld, Christophet ;
Piplai, Aritran .
2024 IEEE INTERNATIONAL CONFERENCE ON ELECTRO INFORMATION TECHNOLOGY, EIT 2024, 2024, :135-144
[22]   Data-Driven Machine Learning Methods for Nontechnical Losses of Electrical Energy Detection: A State-of-the-Art Review [J].
Pazderin, Andrey ;
Kamalov, Firuz ;
Gubin, Pavel Y. ;
Safaraliev, Murodbek ;
Samoylenko, Vladislav ;
Mukhlynin, Nikita ;
Odinaev, Ismoil ;
Zicmane, Inga .
ENERGIES, 2023, 16 (21)
[23]   Machine learning for energy-resource allocation, workflow scheduling and live migration in cloud computing: State-of-the-art survey [J].
Kumar, Yogesh ;
Kaul, Surabhi ;
Hu, Yu-Chen .
SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS, 2022, 36
[24]   A Comparative Study of State-of-the-Art Deep Learning Models for Semantic Segmentation of Pores in Scanning Electron Microscope Images of Activated Carbon [J].
Pokharel, Bishwas ;
Pandey, Deep Shankar ;
Sapkota, Anjuli ;
Yadav, Bhimraj ;
Gurung, Vasanta ;
Adhikari, Mandira Pradhananga ;
Regmi, Lok Nath ;
Adhikari, Nanda Bikram .
IEEE ACCESS, 2024, 12 :50217-50243
[25]   Machine learning methods for compression capacity prediction and sensitivity analysis of concrete-filled steel tubular columns: State-of-the-art review [J].
Zhang, Bohan ;
Yu, Yang ;
Yi, Shanchang ;
Ding, Zhenghao ;
Yousefi, Amir M. ;
Li, Jiehong ;
Lyu, Xuetao .
STRUCTURES, 2025, 72
[26]   3D printing of biodegradable polymers and their composites - Current state-of-the-art, properties, applications, and machine learning for potential future applications [J].
Dananjaya, S. A. V. ;
Chevali, V. S. ;
Dear, J. P. ;
Potluri, P. ;
Abeykoon, C. .
PROGRESS IN MATERIALS SCIENCE, 2024, 146