Research Area:  Machine Learning
In recent years, human society has been witnessed to evolve fast to the era of big data, rendering the data sharing and privacy protection a key issue for the development of digital economies. Federated learning, as a novel pattern for distributed machine learning, is aimed to train a centralized model from decentralized datasets while protecting user privacy, and is now intensively studied in literature. However, a variety of technical challenges, e.g., security issues, incentive mechanism design, are still awaiting further research efforts. In this respect, blockchain proves to be an elegant solution for federated learning to overcome these issues, and thus has been applied in federated learning in many scenarios with success. In this paper, we presented a comprehensive survey for blockchain-enabled federated learning, proposed its technical framework and discussed the key research issues. This work represents the first attempt for reviewing the literature aiming at integrating blockchain and federated learning, and can be expected to offer useful guidance for establishing a new infrastructure for decentralized and secured data circulation, as well as promoting the development of related industries.
Author(s) Name:   Cheng Li; Yong Yuan; Fei-Yue Wang
Conferrence name:   IEEE 1st International Conference on Digital Twins and Parallel Intelligence (DTPI)
Publisher name:  IEEE
Paper Link:   https://ieeexplore.ieee.org/abstract/document/9540163