A Blockchain-Based Auditable Semi-Asynchronous Federated Learning for Heterogeneous Clients
Open Access
- 21 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 133394-133412
Abstract
Federated learning (FL) is a privacy-preserving approach in Artificial Intelligence (AI) that involves exchanging intermediate training parameters instead of raw data, thereby avoiding privacy breaches and promoting effective data collaboration. However, FL still faces several unresolved challenges, including trust issues among participants because traditional FL lacks a mutual consensus auditing mechanism. Another challenge is that when the number of participating nodes is large and resources are heterogeneous; this can lead to low efficiency. To overcome these challenges, we propose a Blockchain-based Auditable Semi-Asynchronous Federated Learning (BASA-FL) system. BASA-FL includes a smart contract that coordinates and records the FL exchange process, enabling the ability to trace and audit the behavior of participating workers. In addition, we proposed an efficient semi-asynchronous approach in blockchain-based distributed FL as the main contribution to addressing heterogeneous problems. We designed a method to quantify worker contributions and distribute rewards based on their contributions. We used a multi-index comprehensive evaluation to motivate workers to maintain high-quality and efficient participation in FL tasks. We conducted several simulations to evaluate the effectiveness of the semi-asynchronous mode, the reliability of the audit mechanism, and the contribution quantification strategy.Keywords
Funding Information
- the MSIT (Ministry of Science and ICT), Korea, under the Special R&D Zone Development Project (R&D) - Development of R&D Innovation Valley support program
This publication has 38 references indexed in Scilit:
- DeepChain: Auditable and Privacy-Preserving Deep Learning with Blockchain-based IncentiveIEEE Transactions on Dependable and Secure Computing, 2019
- Blockchain and Federated Learning for Privacy-Preserved Data Sharing in Industrial IoTIEEE Transactions on Industrial Informatics, 2019
- FLchain: Federated Learning via MEC-enabled Blockchain Network2019
- FLChain: A Blockchain for Auditable Federated Learning with Trust and Incentive2019
- Blockchained On-Device Federated LearningIEEE Communications Letters, 2019
- On Enabling Machine Learning Tasks atop Public Blockchains: A Crowdsourcing Approach2018
- Merkle Tree Traversal in Log Space and Time2004
- Formalizing and Securing Relationships on Public NetworksFirst Monday, 1997
- Federated database systems for managing distributed, heterogeneous, and autonomous databasesACM Computing Surveys, 1990
- A federated architecture for information managementACM Transactions on Information Systems, 1985