Zhizhao Zhang, Tianzhi Yang and Yuan Liu
The purpose of this work is to bridge FL and blockchain technology through designing a blockchain-based smart agent system architecture and applying in FL. and blockchain…
Abstract
Purpose
The purpose of this work is to bridge FL and blockchain technology through designing a blockchain-based smart agent system architecture and applying in FL. and blockchain technology through designing a blockchain-based smart agent system architecture and applying in FL. FL is an emerging collaborative machine learning technique that trains a model across multiple devices or servers holding private data samples without exchanging their data. The locally trained results are aggregated by a centralized server in a privacy-preserving way. However, there is an assumption where the centralized server is trustworthy, which is impractical. Fortunately, blockchain technology has opened a new era of data exchange among trustless strangers because of its decentralized architecture and cryptography-supported techniques.
Design/methodology/approach
In this study, the author proposes a novel design of a smart agent inspired by the smart contract concept. Specifically, based on the proposed smart agent, a fully decentralized, privacy-preserving and fair deep learning blockchain-FL framework is designed, where the agent network is consistent with the blockchain network and each smart agent is a participant in the FL task. During the whole training process, both the data and the model are not at the risk of leakage.
Findings
A demonstration of the proposed architecture is designed to train a neural network. Finally, the implementation of the proposed architecture is conducted in the Ethereum development, showing the effectiveness and applicability of the design.
Originality/value
The author aims to investigate the feasibility and practicality of linking the three areas together, namely, multi-agent system, FL and blockchain. A blockchain-FL framework, which is based on a smart agent system, has been proposed. The author has made several contributions to the state-of-the-art. First of all, a concrete design of a smart agent model is proposed, inspired by the smart contract concept in blockchain. The smart agent is autonomous and is able to disseminate, verify the information and execute the supported protocols. Based on the proposed smart agent model, a new architecture composed by these agents is formed, which is a blockchain network. Then, a fully decentralized, privacy-preserving and smart agent blockchain-FL framework has been proposed, where a smart agent acts as both a peer in a blockchain network and a participant in a FL task at the same time. Finally, a demonstration to train an artificial neural network is implemented to prove the effectiveness of the proposed framework.
Details
Keywords
Cong Ding, Zhizhao Qiao and Zhongyu Piao
The purpose of this study is to design and process the optimal V-shaped microstructure for 7075 aluminum alloy and reveal its wear resistance mechanism and performance.
Abstract
Purpose
The purpose of this study is to design and process the optimal V-shaped microstructure for 7075 aluminum alloy and reveal its wear resistance mechanism and performance.
Design/methodology/approach
The hydrodynamic pressure lubrication models of the nontextured, V-shaped, circular and square microtextures are established. The corresponding oil film pressure distributions are explored. The friction and wear experiments are conducted on a rotating device. The effects of the microstructure shapes and sizes on the wear mechanisms are investigated via the friction coefficients and surface morphologies.
Findings
In comparison, the V-shaped microtexture has the largest oil film carrying capacity and the lowest friction coefficient. The wear mechanism of the V-shaped microtexture is dominated by abrasive and adhesive wear. The V-shaped microtexture has excellent wear resistance under a side length of 300 µm, an interval of 300 µm and a depth of 20 µm.
Originality/value
This study is conductive to the design of wear-resistant surfaces for friction components.
Details
Keywords
The purpose of this paper is to provide a conceptual framework of staged development that examines strategies of domestic companies, government policies, and impacts of foreign…
Abstract
Purpose
The purpose of this paper is to provide a conceptual framework of staged development that examines strategies of domestic companies, government policies, and impacts of foreign multinational companies (MNCs) at different periods of catch‐up of latecomers.
Design/methodology/approach
A multi‐case approach is employed to examine four domestic telecom‐equipment companies that have significant impact on China's telecom‐equipment industry. They are: Huawei Technology Corporation (Huawei), Shenzhen Zhongxin Technology Corporation (ZTE), Datang Telecom Technology Corporation, Ltd (Datang), and Great Dragon Information Technology (GDT).
Findings
This paper identifies four distinct stages of the catching‐up process, featuring different institutional environment, government involvement, and the ensuing actions of foreign MNCs and domestic companies. During the initial stage, China's government decision of directly leapfrogging to the most advanced switch equipment had a profound impact, because it led to both heavy reliance on foreign MNCs and the pursuance of switch research and development (R&D) by domestic research institutes and new technology companies. The dominance of foreign MNCs is challenged during the growth stage, because several domestic companies ascended and gained the capability to produce large‐scale, stored program controls and the government directly leveraged support in R&D, marketing, and finance. Although many uncompetitive domestic companies failed during the filtration stage, the management training received from foreign MNCs and newly available financing options provided necessary resources for some domestic companies to survive and expand. Domestic leaders globalized their marketing, production, and R&D functions and to become MNCs themselves in the globalization stage, thus finalizing the catching‐up.
Social implications
The Chinese experiences shed light on late‐industrialization for other developing economies by suggesting that to catch‐up in high‐tech industries, government can become involved strategically to form a competitive and efficient market environment for innovation.
Originality/value
The paper proposes a new conceptual framework to analyze catching‐up of domestic companies as latecomers. This framework can be used to study catching‐up in other sectors in late‐industrializing countries.