A Fairness-Aware Peer-to-Peer Decentralized Learning Framework with Heterogeneous Devices

被引:6
|
作者
Chen, Zheyi [1 ]
Liao, Weixian [1 ]
Tian, Pu [1 ]
Wang, Qianlong [1 ]
Yu, Wei [1 ]
机构
[1] Towson Univ, Dept Comp & Informat Sci, Towson, MD 21252 USA
关键词
decentralized learning; learning fairness; heterogeneity; INTERNET;
D O I
10.3390/fi14050138
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Distributed machine learning paradigms have benefited from the concurrent advancement of deep learning and the Internet of Things (IoT), among which federated learning is one of the most promising frameworks, where a central server collaborates with local learners to train a global model. The inherent heterogeneity of IoT devices, i.e., non-independent and identically distributed (non-i.i.d.) data, and the inconsistent communication network environment results in the bottleneck of a degraded learning performance and slow convergence. Moreover, most weight averaging-based model aggregation schemes raise learning fairness concerns. In this paper, we propose a peer-to-peer decentralized learning framework to tackle the above issues. Particularly, each local client iteratively finds a learning pair to exchange the local learning model. By doing this, multiple learning objectives are optimized to advocate for learning fairness while avoiding small-group domination. The proposed fairness-aware approach allows local clients to adaptively aggregate the received model based on the local learning performance. The experimental results demonstrate that the proposed approach is capable of significantly improving the efficacy of federated learning and outperforms the state-of-the-art schemes under real-world scenarios, including balanced-i.i.d., unbalanced-i.i.d., balanced-non.i.i.d., and unbalanced-non.i.i.d. environments.
引用
收藏
页数:18
相关论文
共 50 条
  • [11] A congestion-aware search protocol for heterogeneous peer-to-peer networks
    Kin Wah Kwong
    Danny H. K. Tsang
    The Journal of Supercomputing, 2006, 36 : 265 - 282
  • [12] A congestion-aware search protocol for heterogeneous peer-to-peer networks
    Kwong, Kin Wah
    Tsang, Danny H. K.
    JOURNAL OF SUPERCOMPUTING, 2006, 36 (03): : 265 - 282
  • [13] Context aware ubiquitous learning environments for peer-to-peer collaborative learning
    Yang, SJH
    EDUCATIONAL TECHNOLOGY & SOCIETY, 2006, 9 (01): : 188 - 201
  • [14] Mechanism design for decentralized peer-to-peer energy trading considering heterogeneous preferences
    Talari, Saber
    Khorasany, Mohsen
    Razzaghi, Reza
    Ketter, Wolfgang
    Gazafroudi, Amin Shokri
    SUSTAINABLE CITIES AND SOCIETY, 2022, 87
  • [15] Towards a Secure Peer-to-Peer Federated Learning Framework
    Piotrowski, Tim
    Nochta, Zoltan
    ADVANCES IN SERVICE-ORIENTED AND CLOUD COMPUTING, ESOCC 2022, 2022, 1617 : 19 - 31
  • [16] ServiceStore: A Peer-to-Peer Framework for QoS-Aware Service Composition
    Jin, Jun
    Zhang, Yu
    Cao, Yuanda
    Pu, Xing
    Li, Jiaxin
    NETWORK AND PARALLEL COMPUTING, 2010, 6289 : 190 - +
  • [17] Designing a decentralized multi-community peer-to-peer electricity trading framework
    Shafiekhani, Morteza
    Qadrdan, Meysam
    Zhou, Yue
    Wu, Jianzhong
    IET GENERATION TRANSMISSION & DISTRIBUTION, 2024, 18 (19) : 3085 - 3096
  • [18] A Coursepack eBook with Annotation on Mobile Devices for Peer-to-Peer Learning
    Fong, Joseph
    Cheuk, Wai Lok
    2015 INTERNATIONAL SYMPOSIUM ON EDUCATIONAL TECHNOLOGY (ISET 2015), 2015, : 145 - 150
  • [19] ParCop: A decentralized peer-to-peer computing system
    Al-Dmour, NA
    Teahan, WJ
    ISPDC 2004: THIRD INTERNATIONAL SYMPOSIUM ON PARALLEL AND DISTRIBUTED COMPUTING/HETEROPAR '04: THIRD INTERNATIONAL WORKSHOP ON ALGORITHMS, MODELS AND TOOLS FOR PARALLEL COMPUTING ON HETEROGENEOUS NETWORKS, PROCEEDINGS, 2004, : 162 - 168
  • [20] Decentralized identifiers for peer-to-peer service discovery
    Farmer, Carson
    Pick, Sander
    Hill, Andrew
    2021 IFIP NETWORKING CONFERENCE AND WORKSHOPS (IFIP NETWORKING), 2021,