LayerCFL: an efficient federated learning with layer-wised clustering
Abstract Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address this challenge, prior research has introduced clustered FL (CFL), which involves clustering clients and training them separately. Despite its p...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-12-01
|
| Series: | Cybersecurity |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42400-023-00172-x |
| _version_ | 1797397868052480000 |
|---|---|
| author | Jie Yuan Rui Qian Tingting Yuan Mingliang Sun Jirui Li Xiaoyong Li |
| author_facet | Jie Yuan Rui Qian Tingting Yuan Mingliang Sun Jirui Li Xiaoyong Li |
| author_sort | Jie Yuan |
| collection | DOAJ |
| description | Abstract Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address this challenge, prior research has introduced clustered FL (CFL), which involves clustering clients and training them separately. Despite its potential benefits, CFL can be computationally and communicationally expensive when the data distribution is unknown beforehand. This is because CFL involves the entire neural networks of involved clients in computing the clusters during training, which can become increasingly time-consuming with large-sized models. To tackle this issue, this paper proposes an efficient CFL approach called LayerCFL that employs a Layer-wised clustering technique. In LayerCFL, clients are clustered based on a limited number of layers of neural networks that are pre-selected using statistical and experimental methods. Our experimental results demonstrate the effectiveness of LayerCFL in mitigating the impact of Non-IID data, improving the accuracy of clustering, and enhancing computational efficiency. |
| first_indexed | 2024-03-09T01:17:26Z |
| format | Article |
| id | doaj.art-4798fc577624468f9255f8702f252ad2 |
| institution | Directory Open Access Journal |
| issn | 2523-3246 |
| language | English |
| last_indexed | 2024-03-09T01:17:26Z |
| publishDate | 2023-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Cybersecurity |
| spelling | doaj.art-4798fc577624468f9255f8702f252ad22023-12-10T12:22:49ZengSpringerOpenCybersecurity2523-32462023-12-016111410.1186/s42400-023-00172-xLayerCFL: an efficient federated learning with layer-wised clusteringJie Yuan0Rui Qian1Tingting Yuan2Mingliang Sun3Jirui Li4Xiaoyong Li5School of Cyberspace Security, Beijing University of Posts and TelecommunicationsSchool of Cyberspace Security, Beijing University of Posts and TelecommunicationsInstitute of Computer Science, Faculty of Mathematics and Computer Science, University of GoettingenSchool of Cyberspace Security, Beijing University of Posts and TelecommunicationsSchool of Information Technology, Henan University of Chinese MedicineSchool of Cyberspace Security, Beijing University of Posts and TelecommunicationsAbstract Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address this challenge, prior research has introduced clustered FL (CFL), which involves clustering clients and training them separately. Despite its potential benefits, CFL can be computationally and communicationally expensive when the data distribution is unknown beforehand. This is because CFL involves the entire neural networks of involved clients in computing the clusters during training, which can become increasingly time-consuming with large-sized models. To tackle this issue, this paper proposes an efficient CFL approach called LayerCFL that employs a Layer-wised clustering technique. In LayerCFL, clients are clustered based on a limited number of layers of neural networks that are pre-selected using statistical and experimental methods. Our experimental results demonstrate the effectiveness of LayerCFL in mitigating the impact of Non-IID data, improving the accuracy of clustering, and enhancing computational efficiency.https://doi.org/10.1186/s42400-023-00172-xFederated learningClustered federated learningNon-IIDLayer-wised clustering |
| spellingShingle | Jie Yuan Rui Qian Tingting Yuan Mingliang Sun Jirui Li Xiaoyong Li LayerCFL: an efficient federated learning with layer-wised clustering Cybersecurity Federated learning Clustered federated learning Non-IID Layer-wised clustering |
| title | LayerCFL: an efficient federated learning with layer-wised clustering |
| title_full | LayerCFL: an efficient federated learning with layer-wised clustering |
| title_fullStr | LayerCFL: an efficient federated learning with layer-wised clustering |
| title_full_unstemmed | LayerCFL: an efficient federated learning with layer-wised clustering |
| title_short | LayerCFL: an efficient federated learning with layer-wised clustering |
| title_sort | layercfl an efficient federated learning with layer wised clustering |
| topic | Federated learning Clustered federated learning Non-IID Layer-wised clustering |
| url | https://doi.org/10.1186/s42400-023-00172-x |
| work_keys_str_mv | AT jieyuan layercflanefficientfederatedlearningwithlayerwisedclustering AT ruiqian layercflanefficientfederatedlearningwithlayerwisedclustering AT tingtingyuan layercflanefficientfederatedlearningwithlayerwisedclustering AT mingliangsun layercflanefficientfederatedlearningwithlayerwisedclustering AT jiruili layercflanefficientfederatedlearningwithlayerwisedclustering AT xiaoyongli layercflanefficientfederatedlearningwithlayerwisedclustering |