Aggregating intrinsic information to enhance BCI performance through federated learning
Insufficient data is a long-standing challenge for Brain-Computer Interface (BCI) to build a high-performance deep learning model. Though numerous research groups and institutes collect a multitude of EEG datasets for the same BCI task, sharing EEG data from multiple sites is still challenging due t...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/176045 |
| _version_ | 1811694611555418112 |
|---|---|
| author | Liu, Rui Chen, Yuanyuan Li, Anran Ding, Yi Yu, Han Guan, Cuntai |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Liu, Rui Chen, Yuanyuan Li, Anran Ding, Yi Yu, Han Guan, Cuntai |
| author_sort | Liu, Rui |
| collection | NTU |
| description | Insufficient data is a long-standing challenge for Brain-Computer Interface (BCI) to build a high-performance deep learning model. Though numerous research groups and institutes collect a multitude of EEG datasets for the same BCI task, sharing EEG data from multiple sites is still challenging due to the heterogeneity of devices. The significance of this challenge cannot be overstated, given the critical role of data diversity in fostering model robustness. However, existing works rarely discuss this issue, predominantly centering their attention on model training within a single dataset, often in the context of inter-subject or inter-session settings. In this work, we propose a hierarchical personalized Federated Learning EEG decoding (FLEEG) framework to surmount this challenge. This innovative framework heralds a new learning paradigm for BCI, enabling datasets with disparate data formats to collaborate in the model training process. Each client is assigned a specific dataset and trains a hierarchical personalized model to manage diverse data formats and facilitate information exchange. Meanwhile, the server coordinates the training procedure to harness knowledge gleaned from all datasets, thus elevating overall performance. The framework has been evaluated in Motor Imagery (MI) classification with nine EEG datasets collected by different devices but implementing the same MI task. Results demonstrate that the proposed framework can boost classification performance up to 8.4% by enabling knowledge sharing between multiple datasets, especially for smaller datasets. Visualization results also indicate that the proposed framework can empower the local models to put a stable focus on task-related areas, yielding better performance. To the best of our knowledge, this is the first end-to-end solution to address this important challenge. |
| first_indexed | 2024-10-01T07:10:20Z |
| format | Journal Article |
| id | ntu-10356/176045 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:10:20Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1760452024-05-17T15:36:28Z Aggregating intrinsic information to enhance BCI performance through federated learning Liu, Rui Chen, Yuanyuan Li, Anran Ding, Yi Yu, Han Guan, Cuntai School of Computer Science and Engineering Computer and Information Science Federated learning Brain–computer interface Insufficient data is a long-standing challenge for Brain-Computer Interface (BCI) to build a high-performance deep learning model. Though numerous research groups and institutes collect a multitude of EEG datasets for the same BCI task, sharing EEG data from multiple sites is still challenging due to the heterogeneity of devices. The significance of this challenge cannot be overstated, given the critical role of data diversity in fostering model robustness. However, existing works rarely discuss this issue, predominantly centering their attention on model training within a single dataset, often in the context of inter-subject or inter-session settings. In this work, we propose a hierarchical personalized Federated Learning EEG decoding (FLEEG) framework to surmount this challenge. This innovative framework heralds a new learning paradigm for BCI, enabling datasets with disparate data formats to collaborate in the model training process. Each client is assigned a specific dataset and trains a hierarchical personalized model to manage diverse data formats and facilitate information exchange. Meanwhile, the server coordinates the training procedure to harness knowledge gleaned from all datasets, thus elevating overall performance. The framework has been evaluated in Motor Imagery (MI) classification with nine EEG datasets collected by different devices but implementing the same MI task. Results demonstrate that the proposed framework can boost classification performance up to 8.4% by enabling knowledge sharing between multiple datasets, especially for smaller datasets. Visualization results also indicate that the proposed framework can empower the local models to put a stable focus on task-related areas, yielding better performance. To the best of our knowledge, this is the first end-to-end solution to address this important challenge. Agency for Science, Technology and Research (A*STAR) National Research Foundation (NRF) Published version This research/project is supported by the RIE 2020 Advanced Manufacturing and Engineering (AME) Programmatic Fund, Singapore (No. A20G8b0102); and the National Research Foundation, Singapore and DSO National Laboratories under the AI Singapore Programme (AISG Award No: AISG2-RP-2020-019). 2024-05-13T02:31:44Z 2024-05-13T02:31:44Z 2024 Journal Article Liu, R., Chen, Y., Li, A., Ding, Y., Yu, H. & Guan, C. (2024). Aggregating intrinsic information to enhance BCI performance through federated learning. Neural Networks, 172, 106100-. https://dx.doi.org/10.1016/j.neunet.2024.106100 0893-6080 https://hdl.handle.net/10356/176045 10.1016/j.neunet.2024.106100 38232427 2-s2.0-85182710555 172 106100 en A20G8b0102 AISG2-RP-2020-019 Neural Networks © 2024 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC license (http://creativecommons.org/licenses/bync/4.0/). application/pdf |
| spellingShingle | Computer and Information Science Federated learning Brain–computer interface Liu, Rui Chen, Yuanyuan Li, Anran Ding, Yi Yu, Han Guan, Cuntai Aggregating intrinsic information to enhance BCI performance through federated learning |
| title | Aggregating intrinsic information to enhance BCI performance through federated learning |
| title_full | Aggregating intrinsic information to enhance BCI performance through federated learning |
| title_fullStr | Aggregating intrinsic information to enhance BCI performance through federated learning |
| title_full_unstemmed | Aggregating intrinsic information to enhance BCI performance through federated learning |
| title_short | Aggregating intrinsic information to enhance BCI performance through federated learning |
| title_sort | aggregating intrinsic information to enhance bci performance through federated learning |
| topic | Computer and Information Science Federated learning Brain–computer interface |
| url | https://hdl.handle.net/10356/176045 |
| work_keys_str_mv | AT liurui aggregatingintrinsicinformationtoenhancebciperformancethroughfederatedlearning AT chenyuanyuan aggregatingintrinsicinformationtoenhancebciperformancethroughfederatedlearning AT lianran aggregatingintrinsicinformationtoenhancebciperformancethroughfederatedlearning AT dingyi aggregatingintrinsicinformationtoenhancebciperformancethroughfederatedlearning AT yuhan aggregatingintrinsicinformationtoenhancebciperformancethroughfederatedlearning AT guancuntai aggregatingintrinsicinformationtoenhancebciperformancethroughfederatedlearning |