Federated Learning Based on OPTICS Clustering Optimization
Federated learning (FL) has emerged for solving the problem of data fragmentation and isolation in machine learning based on privacy protection. Each client node uploads the trained model parameter information to the central server based on the local training data, and the central server aggregates...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Discrete Dynamics in Nature and Society |
| Online Access: | http://dx.doi.org/10.1155/2022/7151373 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832553688742232064 |
|---|---|
| author | Chenyang Lu Su Deng Yahui Wu Haohao Zhou Wubin Ma |
| author_facet | Chenyang Lu Su Deng Yahui Wu Haohao Zhou Wubin Ma |
| author_sort | Chenyang Lu |
| collection | DOAJ |
| description | Federated learning (FL) has emerged for solving the problem of data fragmentation and isolation in machine learning based on privacy protection. Each client node uploads the trained model parameter information to the central server based on the local training data, and the central server aggregates the parameter information to achieve the purpose of common training. In the real environment, the distribution of data among nodes is often inconsistent. By analyzing the influence of independent identically distributed data (non-IID) on the accuracy of FL, it is shown that the accuracy of the model obtained by the traditional FL method is low. Therefore, we proposed the diversified sampling strategies to simulate the non-IID data situation and came up with the OPTICS (ordering points to identify the clustering structure)-based clustering optimization federated learning method (OCFL), which solves the problem that the learning accuracy is reduced when the data of different nodes are non-IID in FL. Experiments indicate that OCFL greatly improves the model accuracy and training speed compared with the traditional FL algorithm. |
| format | Article |
| id | doaj-art-7d190d5fcb3d49239b121a0f2f6ef115 |
| institution | Kabale University |
| issn | 1607-887X |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Discrete Dynamics in Nature and Society |
| spelling | doaj-art-7d190d5fcb3d49239b121a0f2f6ef1152025-02-03T05:53:29ZengWileyDiscrete Dynamics in Nature and Society1607-887X2022-01-01202210.1155/2022/7151373Federated Learning Based on OPTICS Clustering OptimizationChenyang Lu0Su Deng1Yahui Wu2Haohao Zhou3Wubin Ma4Science and Technology on Information Systems Engineering LaboratoryScience and Technology on Information Systems Engineering LaboratoryScience and Technology on Information Systems Engineering LaboratoryScience and Technology on Information Systems Engineering LaboratoryScience and Technology on Information Systems Engineering LaboratoryFederated learning (FL) has emerged for solving the problem of data fragmentation and isolation in machine learning based on privacy protection. Each client node uploads the trained model parameter information to the central server based on the local training data, and the central server aggregates the parameter information to achieve the purpose of common training. In the real environment, the distribution of data among nodes is often inconsistent. By analyzing the influence of independent identically distributed data (non-IID) on the accuracy of FL, it is shown that the accuracy of the model obtained by the traditional FL method is low. Therefore, we proposed the diversified sampling strategies to simulate the non-IID data situation and came up with the OPTICS (ordering points to identify the clustering structure)-based clustering optimization federated learning method (OCFL), which solves the problem that the learning accuracy is reduced when the data of different nodes are non-IID in FL. Experiments indicate that OCFL greatly improves the model accuracy and training speed compared with the traditional FL algorithm.http://dx.doi.org/10.1155/2022/7151373 |
| spellingShingle | Chenyang Lu Su Deng Yahui Wu Haohao Zhou Wubin Ma Federated Learning Based on OPTICS Clustering Optimization Discrete Dynamics in Nature and Society |
| title | Federated Learning Based on OPTICS Clustering Optimization |
| title_full | Federated Learning Based on OPTICS Clustering Optimization |
| title_fullStr | Federated Learning Based on OPTICS Clustering Optimization |
| title_full_unstemmed | Federated Learning Based on OPTICS Clustering Optimization |
| title_short | Federated Learning Based on OPTICS Clustering Optimization |
| title_sort | federated learning based on optics clustering optimization |
| url | http://dx.doi.org/10.1155/2022/7151373 |
| work_keys_str_mv | AT chenyanglu federatedlearningbasedonopticsclusteringoptimization AT sudeng federatedlearningbasedonopticsclusteringoptimization AT yahuiwu federatedlearningbasedonopticsclusteringoptimization AT haohaozhou federatedlearningbasedonopticsclusteringoptimization AT wubinma federatedlearningbasedonopticsclusteringoptimization |