Personalized Federated Learning with Contextual Modulation and Meta-Learning

被引:0
|
作者
Vettoruzzo, Anna [1 ]
Bouguelia, Mohamed-Rafik [1 ]
Rognvaldsson, Thorsteinn [1 ]
机构
[1] Halmstad Univ, Ctr Appl Intelligent Syst Res CAISR, Halmstad, Sweden
关键词
Personalized federated learning; Meta-learning; Federated learning; Context learning;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Federated learning has emerged as a promising approach for training machine learning models on decentralized data sources while preserving data privacy. However, challenges such as communication bottlenecks, heterogeneity of client devices, and non-i.i.d. data distribution pose significant obstacles to achieving optimal model performance. We propose a novel framework that combines federated learning with meta-learning techniques to enhance both efficiency and generalization capabilities. Our approach introduces a federated modulator that learns contextual information from data batches and uses this knowledge to generate modulation parameters. These parameters dynamically adjust the activations of a base model, which operates using a MAML-based approach for model personalization. Experimental results across diverse datasets highlight the improvements in convergence speed and model performance compared to existing federated learning approaches. These findings highlight the potential of incorporating contextual information and meta-learning techniques into federated learning, paving the way for advancements in distributed machine learning paradigms.
引用
收藏
页码:842 / 850
页数:9
相关论文
共 50 条
  • [1] A Personalized Federated Learning Algorithm Based on Meta-Learning and Knowledge Distillation
    Sun, Yanhua
    Shi, Yahui
    Wang, Zhuwei
    Li, Meng
    Si, Pengbo
    [J]. Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications, 2023, 46 (01): : 12 - 18
  • [2] Personalized Learning with Limited Data on Edge Devices using Federated Learning and Meta-Learning
    Voleti, Kousalya Soumya Lahari
    Ho, Shen-Shyang
    [J]. 2023 IEEE/ACM SYMPOSIUM ON EDGE COMPUTING, SEC 2023, 2023, : 378 - 382
  • [3] Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach
    Fallah, Alireza
    Mokhtari, Aryan
    Ozdaglar, Asuman
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [4] Personalized Federated Learning with Layer-Wise Feature Transformation via Meta-Learning
    Tu, Jingke
    Huang, Jiaming
    Yang, Lei
    Lin, Wanyu
    [J]. ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2024, 18 (04)
  • [5] Personalized Federated Learning Method Based on Attention-Enhanced Meta-Learning Network
    Gao, Yujia
    Wang, Pengfei
    Liu, Liang
    Ma, Huadong
    [J]. Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2024, 61 (01): : 196 - 208
  • [6] Communication-Efficient Personalized Federated Meta-Learning in Edge Networks
    Yu, Feng
    Lin, Hui
    Wang, Xiaoding
    Garg, Sahil
    Kaddoum, Georges
    Singh, Satinder
    Hassan, Mohammad Mehedi
    [J]. IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2023, 20 (02): : 1558 - 1571
  • [7] The Adaptive Personalized Federated Meta-Learning for Anomaly Detection of Industrial Equipment
    Liu, Yuange
    Bao, Zhicheng
    Wang, Yuqian
    Zeng, Xingjie
    Xu, Liang
    Zhang, Weishan
    Zhao, Hongwei
    Yu, Zepei
    [J]. IEEE JOURNAL OF RADIO FREQUENCY IDENTIFICATION, 2022, 6 : 832 - 836
  • [8] Meta-learning and Personalization Layer in Federated Learning
    Bao-Long Nguyen
    Tat Cuong Cao
    Bac Le
    [J]. INTELLIGENT INFORMATION AND DATABASE SYSTEMS, ACIIDS 2022, PT I, 2022, 13757 : 209 - 221
  • [9] TinyReptile: TinyML with Federated Meta-Learning
    Ren, Haoyu
    Anicic, Darko
    Runkler, Thomas A.
    [J]. 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [10] A Collaborative Learning Framework via Federated Meta-Learning
    Lin, Sen
    Yang, Guang
    Zhang, Junshan
    [J]. 2020 IEEE 40TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS), 2020, : 289 - 299