Implementing and evaluating Google federated learning algorithms
Amid data privacy concerns, Federated Learning(FL) has emerged as a promising machine learning paradigm that enables privacy-preserving collaborative model training. However, there exists the need for a platform that matches data owners (supply) with model requesters (demand). This paper will dee...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/148007 |
| _version_ | 1811677605194104832 |
|---|---|
| author | Cicilia Helena |
| author2 | Dusit Niyato |
| author_facet | Dusit Niyato Cicilia Helena |
| author_sort | Cicilia Helena |
| collection | NTU |
| description | Amid data privacy concerns, Federated Learning(FL) has emerged as a promising machine
learning paradigm that enables privacy-preserving collaborative model training. However, there
exists the need for a platform that matches data owners (supply) with model requesters
(demand). This paper will deep dive into some of the components of a working prototype of
CrowdFL, a platform for facilitating the crowdsourcing of FL models. It supports client
selection, model training, and reputation management, which are essential for the FL
crowdsourcing operations. By implementing model training on actual mobile devices, we
demonstrate that the platform improves model performance and training efficiency. |
| first_indexed | 2024-10-01T02:40:01Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/148007 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:40:01Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1480072021-04-22T04:34:57Z Implementing and evaluating Google federated learning algorithms Cicilia Helena Dusit Niyato School of Computer Science and Engineering DNIYATO@ntu.edu.sg Engineering::Computer science and engineering Amid data privacy concerns, Federated Learning(FL) has emerged as a promising machine learning paradigm that enables privacy-preserving collaborative model training. However, there exists the need for a platform that matches data owners (supply) with model requesters (demand). This paper will deep dive into some of the components of a working prototype of CrowdFL, a platform for facilitating the crowdsourcing of FL models. It supports client selection, model training, and reputation management, which are essential for the FL crowdsourcing operations. By implementing model training on actual mobile devices, we demonstrate that the platform improves model performance and training efficiency. Bachelor of Engineering (Computer Engineering) 2021-04-22T04:34:03Z 2021-04-22T04:34:03Z 2021 Final Year Project (FYP) Cicilia Helena (2021). Implementing and evaluating Google federated learning algorithms. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/148007 https://hdl.handle.net/10356/148007 en SCSE20 - 0077 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Cicilia Helena Implementing and evaluating Google federated learning algorithms |
| title | Implementing and evaluating Google federated learning algorithms |
| title_full | Implementing and evaluating Google federated learning algorithms |
| title_fullStr | Implementing and evaluating Google federated learning algorithms |
| title_full_unstemmed | Implementing and evaluating Google federated learning algorithms |
| title_short | Implementing and evaluating Google federated learning algorithms |
| title_sort | implementing and evaluating google federated learning algorithms |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/148007 |
| work_keys_str_mv | AT ciciliahelena implementingandevaluatinggooglefederatedlearningalgorithms |