A Multi-Teacher Distilling Framework With Data Privacy for EEG Emotion Recognition
Authors:
Open Access
- 27 November 2025
- journal article
- Published by IMR Press in Journal of Integrative Neuroscience
- Vol. 24 (11) , 44121
Abstract
Background: This study addressed three key challenges in subject-independent electroencephalography (EEG) emotion recognition: limited data availability, restricted cross-domain knowledge transfer, and suboptimal feature extraction. The aim is to develop an innovative framework that enhances recognition performance while preserving data privacy. Methods: This study introduces a novel multi-teacher knowledge distillation framework that incorporates data privacy considerations. The framework first comprises n subnets, each sequentially trained on distinct EEG datasets without data sharing. The subnets, excluding the initial one, acquire knowledge through the weights and features of all preceding subnets, enabling access to more EEG signals during the training process while maintaining privacy. To enhance cross-domain knowledge transfer, a multi-teacher knowledge distillation strategy was designed, featuring knowledge filters and adaptive multi-teacher knowledge distillation losses. The knowledge filter integrates cross-domain information using a multi-head attention module with a gate mechanism, ensuring effective inheritance of knowledge from all previous subnets. Simultaneously, the adaptive multi-teacher knowledge distillation loss dynamically adjusts the direction of knowledge transfer based on filtered feature similarity, preventing knowledge loss in single-teacher models. Furthermore, a spatio-temporal gate module is proposed to eliminate unnecessary frame-level information from different channels and extract important channels for improved feature representation without requiring expert knowledge. Results: Experimental results demonstrate the superiority of the proposed method over the current state of the art, achieving a 2% performance improvement on the DEAP dataset. Conclusions: The proposed multi-teacher distillation framework with data privacy addresses the challenges of insufficient data availability, limited cross-domain knowledge transfer, and suboptimal feature extraction in subject-independent EEG emotion recognition, demonstrating strong potential for scalable and privacy-preserving emotion recognition applications.Keywords
Funding Information
- National Natural Science Foundation of China (62403264)
- China Postdoctoral Science Foundation (2024M761556)
- Qing-dao Natural Science Foundation (24-4-4-zrjj-94-jch)
- Postdoctoral Innovation Project of Shandong Province (SDCX-ZG 202400312)
- Qingdao Postdoctoral Applied Foundation (QDBSH20240102029)
- Natural Science Foundation of Shandong Province (ZR2025ZD15)
- Systems Science Plus Joint Research Program of Qingdao University (XT2024202)
This publication has 57 references indexed in Scilit:
- Convolutional gated recurrent unit-driven multidimensional dynamic graph neural network for subject-independent emotion recognitionExpert Systems with Applications, 2023
- High definition transcranial direct current stimulation of the Cz improves social dysfunction in children with autism spectrum disorder: A randomized, sham, controlled studyAutism Research, 2023
- Multi-teacher Knowledge Distillation for End-to-End Text Image Machine Translation2023
- MTLFuseNet: A novel emotion recognition model based on deep latent feature fusion of EEG signals and multi-task learningKnowledge-Based Systems, 2023
- Multi-teacher knowledge distillation based on joint Guidance of Probe and Adaptive CorrectorNeural Networks, 2023
- EEG-based BCI: A novel improvement for EEG signals classification based on real-time preprocessingComputers in Biology and Medicine, 2022
- EEG emotion recognition using fusion model of graph convolutional neural networks and LSTMApplied Soft Computing, 2021
- A review on transfer learning in EEG signal analysisNeurocomputing, 2021
- Adaptive multi-teacher multi-level knowledge distillationNeurocomputing, 2020
- EEG-based emotion recognition using an end-to-end regional-asymmetric convolutional neural networkKnowledge-Based Systems, 2020