High-performance federated continual learning algorithm for heterogeneous streaming data
Aiming at the problems of poor model performance and low training efficiency in training streaming data of AI models that provide intelligent services, a high-performance federated continual learning algorithm for heterogeneous streaming data (FCL-HSD) was proposed in the distributed terminal system...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2023-05-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023102/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539188537688064 |
|---|---|
| author | Hui JIANG Tianliu HE Min LIU Sheng SUN Yuwei WANG |
| author_facet | Hui JIANG Tianliu HE Min LIU Sheng SUN Yuwei WANG |
| author_sort | Hui JIANG |
| collection | DOAJ |
| description | Aiming at the problems of poor model performance and low training efficiency in training streaming data of AI models that provide intelligent services, a high-performance federated continual learning algorithm for heterogeneous streaming data (FCL-HSD) was proposed in the distributed terminal system with privacy data.In order to solve the problem of the current model forgetting old data, a model with dynamically extensible structure was introduced in the local training stage, and an extension audit mechanism was designed to ensure the capability of the AI model to recognize old data at the cost of small storage overhead.Considering the heterogeneity of terminal data, a customized global model strategy based on data distribution similarity was designed at the central server side, and an aggregation-by-block manner was implemented for different modules of the model.The feasibility and effectiveness of the proposed algorithm were verified under various data increment scenarios with different data sets.Experimental results show that, compared with existing works, the proposed algorithm can effectively improve the model performance to classify old data on the premise of ensuring the capability to classify new data. |
| format | Article |
| id | doaj-art-4939bd0b7bad46939dfa56706c1121cf |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2023-05-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-4939bd0b7bad46939dfa56706c1121cf2025-01-14T07:23:53ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2023-05-014412313659838278High-performance federated continual learning algorithm for heterogeneous streaming dataHui JIANGTianliu HEMin LIUSheng SUNYuwei WANGAiming at the problems of poor model performance and low training efficiency in training streaming data of AI models that provide intelligent services, a high-performance federated continual learning algorithm for heterogeneous streaming data (FCL-HSD) was proposed in the distributed terminal system with privacy data.In order to solve the problem of the current model forgetting old data, a model with dynamically extensible structure was introduced in the local training stage, and an extension audit mechanism was designed to ensure the capability of the AI model to recognize old data at the cost of small storage overhead.Considering the heterogeneity of terminal data, a customized global model strategy based on data distribution similarity was designed at the central server side, and an aggregation-by-block manner was implemented for different modules of the model.The feasibility and effectiveness of the proposed algorithm were verified under various data increment scenarios with different data sets.Experimental results show that, compared with existing works, the proposed algorithm can effectively improve the model performance to classify old data on the premise of ensuring the capability to classify new data.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023102/heterogeneous datastreaming datafederated learningfederated continual learningcatastrophic forgetting |
| spellingShingle | Hui JIANG Tianliu HE Min LIU Sheng SUN Yuwei WANG High-performance federated continual learning algorithm for heterogeneous streaming data Tongxin xuebao heterogeneous data streaming data federated learning federated continual learning catastrophic forgetting |
| title | High-performance federated continual learning algorithm for heterogeneous streaming data |
| title_full | High-performance federated continual learning algorithm for heterogeneous streaming data |
| title_fullStr | High-performance federated continual learning algorithm for heterogeneous streaming data |
| title_full_unstemmed | High-performance federated continual learning algorithm for heterogeneous streaming data |
| title_short | High-performance federated continual learning algorithm for heterogeneous streaming data |
| title_sort | high performance federated continual learning algorithm for heterogeneous streaming data |
| topic | heterogeneous data streaming data federated learning federated continual learning catastrophic forgetting |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023102/ |
| work_keys_str_mv | AT huijiang highperformancefederatedcontinuallearningalgorithmforheterogeneousstreamingdata AT tianliuhe highperformancefederatedcontinuallearningalgorithmforheterogeneousstreamingdata AT minliu highperformancefederatedcontinuallearningalgorithmforheterogeneousstreamingdata AT shengsun highperformancefederatedcontinuallearningalgorithmforheterogeneousstreamingdata AT yuweiwang highperformancefederatedcontinuallearningalgorithmforheterogeneousstreamingdata |