RMKD: Relaxed matching knowledge distillation for short-length SSVEP-based brain–computer interfaces

• Published in: Neural networks Vol. 185; p. 107133
• Main Authors: Lan, Zhen, Li, Zixing, Yan, Chao, Xiang, Xiaojia, Tang, Dengqing, Wu, Min, Chen, Zhenghua
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.05.2025
• Subjects: Algorithms; Brain - physiology; Brain-Computer Interfaces; Brain–computer interface (BCI); Electroencephalogram (EEG); Electroencephalography - methods; Evoked Potentials, Visual - physiology; Humans; Knowledge distillation; Short-length signals; Steady-state visual evoked potential (SSVEP); Steady-state visual evoked potential (SSVEP); Electroencephalogram (EEG); Short-length signals; Knowledge distillation; Brain–computer interface (BCI)
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2025.107133

Accurate decoding of electroencephalogram (EEG) signals in the shortest possible time is essential for the realization of a high-performance brain–computer interface (BCI) system based on the steady-state visual evoked potential (SSVEP). However, the degradation of decoding performance of short-length EEG signals is often unavoidable due to the reduced information, which hinders the development of BCI systems in real-world applications. In this paper, we propose a relaxed matching knowledge distillation (RMKD) method to transfer both feature-level and logit-level knowledge in a relaxed manner to improve the decoding performance of short-length EEG signals. Specifically, the long-length EEG signals and short-length EEG signals are decoded into the frequency representation by the teacher and student models, respectively. At the feature-level, the frequency-masked generation distillation is designed to improve the representation ability of student features by forcing the randomly masked student features to generate full teacher features. At the logit-level, the non-target class knowledge distillation and the inter-class relation distillation are combined to mitigate loss conflicts by imitating the distribution of non-target classes and preserve the inter-class relation in the prediction vectors of the teacher and student models. We conduct comprehensive experiments on two public SSVEP datasets in the subject-independent scenario with six different signal lengths. The extensive experimental results demonstrate that the proposed RMKD method has significantly improved the decoding performance of short-length EEG signals in SSVEP-based BCI systems.