Uplink Scheduling in Federated Learning: an Importance-Aware Approach via Graph Representation Learning

被引:0
|
作者
Skocaj, Marco [1 ,2 ]
Rivera, Pedro Enrique Iturria [3 ]
Verdone, Roberto [1 ,2 ]
Erol-Kantarci, Melike [3 ]
机构
[1] Univ Bologna, DEI, Bologna, Italy
[2] CNIT, WiLab, Natl Lab Wireless Commun, Parma, Italy
[3] Univ Ottawa, Sch Elect Engn & Comp Sci, Ottawa, ON, Canada
关键词
Federated Learning; Graph Representation Learning; Scheduling; Communication-efficient FL; Energy-efficient FL; 6G; Spatial Correlation;
D O I
10.1109/ICCWORKSHOPS57953.2023.10283576
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Federated Learning (FL) has emerged as a promising framework for distributed training of AI-based services, applications, and network procedures in 6G. One of the major challenges affecting the performance and efficiency of 6G wireless FL systems is the massive scheduling of user devices over resource-constrained channels. In this work, we argue that the uplink scheduling of FL client devices is a problem with a rich relational structure. To address this challenge, we propose a novel, energy-efficient, and importance-aware metric for client scheduling in FL applications by leveraging Unsupervised Graph Representation Learning (UGRL). Our proposed approach introduces a relational inductive bias in the scheduling process and does not require the collection of training feedback information from client devices, unlike state-of-the-art importance-aware mechanisms. We evaluate our proposed solution against baseline scheduling algorithms based on recently proposed metrics in the literature. Results show that, when considering scenarios of nodes exhibiting spatial relations, our approach can achieve an average gain of up to 10% in model accuracy and up to 17 times in energy efficiency compared to state-of-the-art importance-aware policies.
引用
收藏
页码:1014 / 1019
页数:6
相关论文
共 50 条
  • [31] Generalized Federated Learning via Sharpness Aware Minimization
    Qu, Zhe
    Li, Xingyu
    Duan, Rui
    Liu, Yao
    Tang, Bo
    Lu, Zhuo
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [32] Class-aware graph Siamese representation learning
    Xu, Chengcheng
    Wang, Tianfeng
    Chen, Man
    Chen, Jun
    Pan, Zhisong
    NEUROCOMPUTING, 2025, 620
  • [33] Motif-Aware Adversarial Graph Representation Learning
    Zhao, Ming
    Zhang, Yinglong
    Xia, Xuewen
    Xu, Xing
    IEEE ACCESS, 2022, 10 : 8617 - 8626
  • [34] Structure-Aware Transformer for Graph Representation Learning
    Chen, Dexiong
    O'Bray, Leslie
    Borgwardt, Karsten
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [35] Scheduling for Cellular Federated Edge Learning With Importance and Channel Awareness
    Ren, Jinke
    He, Yinghui
    Wen, Dingzhu
    Yu, Guanding
    Huang, Kaibin
    Guo, Dongning
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2020, 19 (11) : 7690 - 7703
  • [36] Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning
    Qiao, Ziyue
    Wang, Pengyang
    Fu, Yanjie
    Du, Yi
    Wang, Pengfei
    Zhou, Yuanchun
    20TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2020), 2020, : 432 - 441
  • [37] Decentralized Federated Graph Learning via Surrogate Model
    Zhang, Bolin
    Gu, Ruichun
    Liu, Haiying
    CMC-COMPUTERS MATERIALS & CONTINUA, 2025, 82 (02): : 2521 - 2535
  • [38] FedLSF: Federated Local Graph Learning via Specformers
    Samarth, Ram
    Annappa, B.
    Sachin, D. N.
    2024 20TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING IN SMART SYSTEMS AND THE INTERNET OF THINGS, DCOSS-IOT 2024, 2024, : 187 - 194
  • [39] Semantic Grasping Via a Knowledge Graph of Robotic Manipulation: A Graph Representation Learning Approach
    Kwak, Ji Ho
    Lee, Jaejun
    Whang, Joyce Jiyoung
    Jo, Sungho
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (04): : 9397 - 9404
  • [40] QMNet: Importance-Aware Message Exchange for Decentralized Multi-Agent Reinforcement Learning
    Huang, Xiufeng
    Zhou, Sheng
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (05) : 4739 - 4751