Homophily Learning-Based Federated Intelligence: A Case Study on Industrial IoT Equipment Failure Prediction

Federated learning is an emerging distributed machine learning paradigm that can break through data silos and make use of data from different clients in a secure way. However, for deep neural networks in federated learning, the models on clients may learn the same pattern with different weight distr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE internet of things journal 2023-04, Vol.10 (8), p.7356-7365
Hauptverfasser: Zeng, Xingjie, Yu, Zepei, Zhang, Weishan, Wang, Xiao, Lu, Qinghua, Wang, Tao, Gu, Mu, Tian, Yonglin, Wang, Fei-Yue
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Federated learning is an emerging distributed machine learning paradigm that can break through data silos and make use of data from different clients in a secure way. However, for deep neural networks in federated learning, the models on clients may learn the same pattern with different weight distributions despite the same data distribution of local data sets, which limits the performance of neural networks after weight fusions. Therefore, in this article, we propose a homophily learning-based federated intelligence (HLFI) approach, where hierarchical federated learning strategy and dynamic elimination learning strategy are designed to alleviate the problem. The experiments on equipment failure prediction show that the proposed approach can improve the failure prediction F1-score up to 9.32%. Our approach also has good generalization capabilities and can be applied in other federated learning methods to improve the model performance.
ISSN:2327-4662
2327-4662
DOI:10.1109/JIOT.2022.3228792