Social-Aware Distributed Meta-Learning: A Perspective of Constrained Graphical Bandits

doi:10.1109/ICC45041.2023.10278850

	Social-Aware Distributed Meta-Learning: A Perspective of Constrained Graphical Bandits
	Shangshang Wang; Simeng Bian; Yinxu Tang; Ziyu Shao
	2023
会议录名称	IEEE ICC 2023
ISSN	1938-1883
卷号	2023-May
页码	4385-4390
发表状态	已发表
DOI	10.1109/ICC45041.2023.10278850
摘要	Meta-learning has earned its wide popularity to handle a family of similar tasks (e.g., classification of pets and wildlife) with elaborately trained meta-knowledge (e.g., shared network architecture and neural network parameter initialization). In this paper, we focus on the distributed training of meta-knowledge via server-device collaboration at the edge (i.e., distributed meta-learning). Notably, its practical implementation often runs into concerns like 1) time-varying unknown wireless dynamics (e.g., transmission latency); 2) device-side fair device involvement in distributed training; 3) server-side resource efficiency. To address such concerns, 1) we employ online learning to estimate the unknown dynamics and further exploit social ties among device users to accelerate online learning; 2) we utilize online control techniques to handle long-term fairness and resource constraints. By characterizing inter-user social ties as a social graph, we study distributed meta-learning from the perspective of constrained graphical bandits. Therefore, we propose a SoCial-awarE meta-kNowledge dispaTch (SCENT) algorithm by effectively integrating graphical bandit learning and online control. Besides a sublinear regret (i.e., loss of performance), SCENT also guarantees a well-trained meta-knowledge under within-budget resource consumption and fair device involvement. We conduct simulations to justify the outperformance of SCENT compared with baselines. © 2023 IEEE.
关键词	Metalearning Training Wireless communication Performance evaluation Simulation Wildlife Neural networks
会议名称	2023 IEEE International Conference on Communications, ICC 2023
会议地点	Rome, Italy
会议日期	28 May-1 June 2023
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20234815114432
EI主题词	Network architecture
原始文献类型	Conference article (CA)
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/281927
专题	信息科学与技术学院信息科学与技术学院_PI研究组_邵子瑜组信息科学与技术学院_硕士生信息科学与技术学院_博士生
作者单位	School of Information Science and Technology, ShanghaiTech University, Shanghai, China
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Shangshang Wang,Simeng Bian,Yinxu Tang,et al. Social-Aware Distributed Meta-Learning: A Perspective of Constrained Graphical Bandits[C]:Institute of Electrical and Electronics Engineers Inc.,2023:4385-4390.