Common Language for Goal-Oriented Semantic Communications: A Curriculum Learning Framework

被引:16
作者
Farshbafan, Mohammad Karimzadeh [1 ]
Saad, Walid [1 ]
Debbah, Merouane [2 ,3 ]
机构
[1] Virginia Tech, Wireless VT Bradley, Dept Elect & Comp Engn, Blacksburg, VA USA
[2] Technol Innovat Inst, Abu Dhabi, U Arab Emirates
[3] Mohamed Bin Zayed Univ Artificial Intelligence, POB 9639, Masdar City, Abu Dhabi, U Arab Emirates
来源
IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022) | 2022年
关键词
Semantic communication; Goal-Oriented Communication; Reinforcement Learning; Curriculum Learning;
D O I
10.1109/ICC45855.2022.9838724
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
Semantic communications will play a critical role in enabling goal-oriented services over next-generation wireless systems. However, most prior art in this domain is restricted to specific applications (e.g., text or image), and it does not enable goal-oriented communications in which the effectiveness of the transmitted information must be considered along with the semantics so as to execute a certain task. In this paper, a comprehensive semantic communications framework is proposed for enabling goal-oriented task execution. To capture the semantics between a speaker and a listener, a common language is defined using the concept of beliefs to enable the speaker to describe the environment observations to the listener. Then, an optimization problem is posed to choose the minimum set of beliefs that perfectly describes the observation while minimizing the task execution time and transmission cost. A novel top-down framework that combines curriculum learning (CL) and reinforcement learning (RL) is proposed to solve this problem. Simulation results show that the proposed CL method outperforms traditional RL in terms of convergence time, task execution time, and transmission cost during training.
引用
收藏
页码:1710 / 1715
页数:6
相关论文
共 11 条
[1]   Semantic Reasoning for Context-Aware Internet of Things Applications [J].
A, Maarala, I ;
Su, Xiang ;
Riekki, Jukka .
IEEE INTERNET OF THINGS JOURNAL, 2017, 4 (02) :461-473
[2]   The Semantic Communication Game [J].
Guler, Basak ;
Yener, Aylin ;
Swami, Ananthram .
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2018, 4 (04) :787-802
[3]  
Lu K., 2021, ARXIV210812121
[4]  
Narvekar Sanmit, 2020, ARXIV200304960
[5]   Semantic-Effectiveness Filtering and Control for Post-5G Wireless Connectivity [J].
Popovski, Petar ;
Simeone, Osvaldo ;
Boccardi, Federico ;
Gunduz, Deniz ;
Sahin, Onur .
JOURNAL OF THE INDIAN INSTITUTE OF SCIENCE, 2020, 100 (02) :435-443
[6]  
Seo H., 2021, ARXIV210805681
[7]  
Sutton RS, 2018, ADAPT COMPUT MACH LE, P1
[8]  
Tucker M., 2021, ARXIV210801828
[9]  
Xie H., 2020, IEEE J SELECTED AREA, V39, P142
[10]   Deep Learning Enabled Semantic Communication Systems [J].
Xie, Huiqiang ;
Qin, Zhijin ;
Li, Geoffrey Ye ;
Juang, Biing-Hwang .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2021, 69 :2663-2675