FGC: GCN-Based Federated Learning Approach for Trust Industrial Service Recommendation
- Authors
- Yin, Yuyu; Li, Youhuizi; Gao, Honghao; Liang, Tingting; Pan, Qianqian
- Issue Date
- Mar-2023
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Industrial Internet of Things; Data privacy; Federated learning; Data models; Servers; Training; Informatics; federated learning (FL); graph convolutional neural network (GCN); trust industrial service recommendation
- Citation
- IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, v.19, no.3, pp.3240 - 3250
- Journal Title
- IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
- Volume
- 19
- Number
- 3
- Start Page
- 3240
- End Page
- 3250
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/87797
- DOI
- 10.1109/TII.2022.3214308
- ISSN
- 1551-3203
- Abstract
- With the development of the Industrial Internet of Things system, the huge amount of devices, services, and continuous data, making it difficult to discover a trusted service in complex scenarios. To better leverage knowledge and historical behavior, recommendation systems are applied. However, the model accuracy closely depends on training data size; there is a great risk of data leaking by collecting from multiple departments. To solve these problems, we propose a graph-convolutional-neural-network-based federated approach, which accurately recommends proper service for participating clients without gathering the raw data. Specifically, each client trains locally and uploads the weights of their model to the server for aggregation. Besides, the potential overlapping services of different clients are leveraged to guide the embedding aggregation and sharing, which, in turn, optimize the local training results. Their sensitive scenarios' embedding is kept locally. Owing to the model aggregation, it also resists the poisoning attack to some degree. In addition, the comprehensive experiments on classic public recommendation datasets evaluate the feasibility, effectiveness, trustworthiness, and potential influences.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/87797)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.