BlockFL: blockchain-enabled decentralized federated learning and model trading
Federated Learning (FL) is a promising privacy-preserving distributed machine learning paradigm. However, there is only a centralized parameter server to aggregate all the local model updates, which brings the challenges of a single point of failure and server overload, especially in large-scale tra...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/156495 |
| _version_ | 1826121523286507520 |
|---|---|
| author | Pham, Tan Anh Khoa |
| author2 | Dusit Niyato |
| author_facet | Dusit Niyato Pham, Tan Anh Khoa |
| author_sort | Pham, Tan Anh Khoa |
| collection | NTU |
| description | Federated Learning (FL) is a promising privacy-preserving distributed machine learning paradigm. However, there is only a centralized parameter server to aggregate all the local model updates, which brings the challenges of a single point of failure and server overload, especially in large-scale training scenarios. To achieve secure, reliable, and scalable FL, we leverage a sharding technique to improve scalability of the Blockchain-based Federated Edge Learning (BFEL) framework with a main chain and multiple subchains in [Kang et al., 2020]. Specifically, to release the cross-chain transaction processing workload of the main chain, the number of working consensus nodes for the main chain can be divided into multiple clusters to process multiple cross-chain transactions in parallel. This method helps reduce the execution time for FL task training and improve transaction throughput on the main chain. This project presents a working prototype to utilize blockchain and sharding techniques, thereby scaling up decentralized FL for secure, scalable and large-scale FL task training. |
| first_indexed | 2024-10-01T05:33:59Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/156495 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:33:59Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1564952022-04-17T13:32:06Z BlockFL: blockchain-enabled decentralized federated learning and model trading Pham, Tan Anh Khoa Dusit Niyato School of Computer Science and Engineering DNIYATO@ntu.edu.sg Engineering::Computer science and engineering Federated Learning (FL) is a promising privacy-preserving distributed machine learning paradigm. However, there is only a centralized parameter server to aggregate all the local model updates, which brings the challenges of a single point of failure and server overload, especially in large-scale training scenarios. To achieve secure, reliable, and scalable FL, we leverage a sharding technique to improve scalability of the Blockchain-based Federated Edge Learning (BFEL) framework with a main chain and multiple subchains in [Kang et al., 2020]. Specifically, to release the cross-chain transaction processing workload of the main chain, the number of working consensus nodes for the main chain can be divided into multiple clusters to process multiple cross-chain transactions in parallel. This method helps reduce the execution time for FL task training and improve transaction throughput on the main chain. This project presents a working prototype to utilize blockchain and sharding techniques, thereby scaling up decentralized FL for secure, scalable and large-scale FL task training. Bachelor of Engineering (Computer Science) 2022-04-17T13:32:06Z 2022-04-17T13:32:06Z 2022 Final Year Project (FYP) Pham, T. A. K. (2022). BlockFL: blockchain-enabled decentralized federated learning and model trading. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156495 https://hdl.handle.net/10356/156495 en SCSE21-0198 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Pham, Tan Anh Khoa BlockFL: blockchain-enabled decentralized federated learning and model trading |
| title | BlockFL: blockchain-enabled decentralized federated learning and model trading |
| title_full | BlockFL: blockchain-enabled decentralized federated learning and model trading |
| title_fullStr | BlockFL: blockchain-enabled decentralized federated learning and model trading |
| title_full_unstemmed | BlockFL: blockchain-enabled decentralized federated learning and model trading |
| title_short | BlockFL: blockchain-enabled decentralized federated learning and model trading |
| title_sort | blockfl blockchain enabled decentralized federated learning and model trading |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/156495 |
| work_keys_str_mv | AT phamtananhkhoa blockflblockchainenableddecentralizedfederatedlearningandmodeltrading |